{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/llama","slug":"llama","name":"LLaMA","full_name":"LLaMA","full_name_withheld":false,"description_markdown":"**LLaMA** is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were subsequently proposed. The main difference with the original architecture are listed below.\r\n\r\n- RMSNorm normalizing function is used to improve the training stability, by normalizing the input of each transformer sub-layer, instead of normalizing the output.\r\n- The ReLU non-linearity is replaced by the SwiGLU activation function to improve performance.\r\n- Absolute positional embeddings are removed and instead rotary positional embeddings (RoPE) are added at each layer of the network.","description_state":"present","introduced_year":null,"introduced_by":{"title":"LLaMA: Open and Efficient Foundation Language Models","paper":"/paper/llama-open-and-efficient-foundation-language-1","first_author":"Hugo Touvron","n_authors":14,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/llama-open-and-efficient-foundation-language-1"},"source":{"url":"https://arxiv.org/abs/2302.13971v1","title":"LLaMA: Open and Efficient Foundation Language Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":1062,"archive_num_papers":1062,"papers_newest_first":[{"paper":"/paper/making-language-model-a-hierarchical","slug":"making-language-model-a-hierarchical","title":"Making Language Model a Hierarchical Classifier and Generator","date":"2025-07-17","arxiv_id":"2507.12930","n_code_links":1,"syntology":null},{"paper":"/paper/simplifications-are-absolutists-how","slug":"simplifications-are-absolutists-how","title":"Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions","date":"2025-07-16","arxiv_id":"2507.11981","n_code_links":1,"syntology":null},{"paper":"/paper/seq-vs-seq-an-open-suite-of-paired-encoders","slug":"seq-vs-seq-an-open-suite-of-paired-encoders","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","date":"2025-07-15","arxiv_id":"2507.11412","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jhu-clsp/ettin-encoder-vs-decoder"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"compactor-calibrated-query-agnostic-kv-cache","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","date":"2025-07-10","arxiv_id":"2507.08143","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-habitat-robotics-using-large","title":"Evaluation of Habitat Robotics using Large Language Models","date":"2025-07-08","arxiv_id":"2507.06157","n_code_links":0,"syntology":null},{"paper":null,"slug":"musiscene-leveraging-mu-llama-for-scene","title":"MusiScene: Leveraging MU-LLaMA for Scene Imagination and Enhanced Video Background Music Generation","date":"2025-07-08","arxiv_id":"2507.05894","n_code_links":0,"syntology":null},{"paper":"/paper/any4-learned-4-bit-numeric-representation-for","slug":"any4-learned-4-bit-numeric-representation-for","title":"any4: Learned 4-bit Numeric Representation for LLMs","date":"2025-07-07","arxiv_id":"2507.04610","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/any4"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"model-inversion-attacks-on-llama-3-extracting","title":"Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models","date":"2025-07-06","arxiv_id":"2507.04478","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-acing-chartered","title":"Large Language Models Acing Chartered Accountancy","date":"2025-06-26","arxiv_id":"2506.21031","n_code_links":0,"syntology":null},{"paper":null,"slug":"ccrs-a-zero-shot-llm-as-a-judge-framework-for","title":"CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation","date":"2025-06-25","arxiv_id":"2506.20128","n_code_links":0,"syntology":null},{"paper":"/paper/octothinker-mid-training-incentivizes","slug":"octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","arxiv_id":"2506.20512","n_code_links":1,"syntology":{"ran":16,"of":17,"n_ran_checked":6,"n_instrument":10,"unverified":1,"pointer_only":4,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gair-nlp/octothinker"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-llms-replace-humans-during-code-chunking","title":"Can LLMs Replace Humans During Code Chunking?","date":"2025-06-24","arxiv_id":"2506.19897","n_code_links":0,"syntology":null},{"paper":null,"slug":"mental-health-equity-in-llms-leveraging-multi","title":"Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives","date":"2025-06-22","arxiv_id":"2506.18116","n_code_links":0,"syntology":null},{"paper":"/paper/pre-trained-llm-is-a-semantic-aware-and","slug":"pre-trained-llm-is-a-semantic-aware-and","title":"Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster","date":"2025-06-22","arxiv_id":"2506.18034","n_code_links":1,"syntology":null},{"paper":null,"slug":"shrinking-the-generation-verification-gap","title":"Shrinking the Generation-Verification Gap with Weak Verifiers","date":"2025-06-22","arxiv_id":"2506.18203","n_code_links":0,"syntology":null},{"paper":"/paper/a-minimalist-optimizer-design-for-llm","slug":"a-minimalist-optimizer-design-for-llm","title":"A Minimalist Optimizer Design for LLM Pretraining","date":"2025-06-20","arxiv_id":"2506.16659","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["optimai-lab/minimalist_llm_pretraining"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/all-is-not-lost-llm-recovery-without","slug":"all-is-not-lost-llm-recovery-without","title":"All is Not Lost: LLM Recovery without Checkpoints","date":"2025-06-18","arxiv_id":"2506.15461","n_code_links":1,"syntology":null},{"paper":null,"slug":"i-know-which-llm-wrote-your-code-last-summer","title":"I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution","date":"2025-06-18","arxiv_id":"2506.17323","n_code_links":0,"syntology":null},{"paper":null,"slug":"phantomhunter-detecting-unseen-privately","title":"PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning","date":"2025-06-18","arxiv_id":"2506.15683","n_code_links":0,"syntology":null},{"paper":"/paper/arctic-long-sequence-training-scalable-and","slug":"arctic-long-sequence-training-scalable-and","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","date":"2025-06-16","arxiv_id":"2506.13996","n_code_links":2,"syntology":null},{"paper":"/paper/attribution-guided-pruning-for-compression","slug":"attribution-guided-pruning-for-compression","title":"Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs","date":"2025-06-16","arxiv_id":"2506.13727","n_code_links":1,"syntology":null},{"paper":null,"slug":"delving-into-the-psychology-of-machines","title":"Delving Into the Psychology of Machines: Exploring the Structure of Self-Regulated Learning via LLM-Generated Survey Responses","date":"2025-06-16","arxiv_id":"2506.13384","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-for-phishing","slug":"evaluating-large-language-models-for-phishing","title":"Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability","date":"2025-06-16","arxiv_id":"2506.13746","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-models-enable-data-augmented","title":"Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials","date":"2025-06-14","arxiv_id":"2506.12557","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-llm-merging-for-multi-task","slug":"training-free-llm-merging-for-multi-task","title":"Training-free LLM Merging for Multi-task Learning","date":"2025-06-14","arxiv_id":"2506.12379","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-homogeneous-attention-memory-efficient","title":"Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache","date":"2025-06-13","arxiv_id":"2506.11886","n_code_links":0,"syntology":null},{"paper":null,"slug":"infoflood-jailbreaking-large-language-models","title":"InfoFlood: Jailbreaking Large Language Models with Information Overload","date":"2025-06-13","arxiv_id":"2506.12274","n_code_links":0,"syntology":null},{"paper":null,"slug":"2506-10527","title":"LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs","date":"2025-06-12","arxiv_id":"2506.10527","n_code_links":0,"syntology":null},{"paper":null,"slug":"2506-10585","title":"Primender Sequence: A Novel Mathematical Construct for Testing Symbolic Inference and AI Reasoning","date":"2025-06-12","arxiv_id":"2506.10585","n_code_links":0,"syntology":null},{"paper":null,"slug":"contemporary-ai-foundation-models-increase","title":"Contemporary AI foundation models increase biological weapons risk","date":"2025-06-12","arxiv_id":"2506.13798","n_code_links":0,"syntology":null},{"paper":"/paper/decomposing-mlp-activations-into","slug":"decomposing-mlp-activations-into","title":"Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization","date":"2025-06-12","arxiv_id":"2506.10920","n_code_links":1,"syntology":null},{"paper":"/paper/counselbench-a-large-scale-expert-evaluation","slug":"counselbench-a-large-scale-expert-evaluation","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmark of Large Language Models in Mental Health Counseling","date":"2025-06-10","arxiv_id":"2506.08584","n_code_links":1,"syntology":null},{"paper":null,"slug":"fairness-is-not-silence-unmasking-vacuous","title":"Fairness is Not Silence: Unmasking Vacuous Neutrality in Small Language Models","date":"2025-06-10","arxiv_id":"2506.08487","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-fine-tuning-in-llama-on","title":"The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation","date":"2025-06-10","arxiv_id":"2506.08827","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-as-individuals-evolve-as-a-team-multi","title":"Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments","date":"2025-06-08","arxiv_id":"2506.07232","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-and-civil-discourse","title":"Artificial Intelligence and Civil Discourse: How LLMs Moderate Climate Change Conversations","date":"2025-06-07","arxiv_id":"2506.12077","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-large-language-models-on-3","title":"Benchmarking Large Language Models on Homework Assessment in Circuit Analysis","date":"2025-06-05","arxiv_id":"2506.06390","n_code_links":0,"syntology":null},{"paper":"/paper/flex-travelplanner-a-benchmark-for-flexible","slug":"flex-travelplanner-a-benchmark-for-flexible","title":"Flex-TravelPlanner: A Benchmark for Flexible Planning with Language Agents","date":"2025-06-05","arxiv_id":"2506.04649","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["juhyunohh/flextravelbench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multiple-choice-question-generation-using","title":"Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights","date":"2025-06-05","arxiv_id":"2506.04851","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-interaction-with-databases","title":"Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things","date":"2025-06-05","arxiv_id":"2506.06396","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-common-pile-v0-1-an-8tb-dataset-of-public","title":"The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text","date":"2025-06-05","arxiv_id":"2506.05209","n_code_links":0,"syntology":null},{"paper":null,"slug":"facts-are-harder-than-opinions-a-multilingual","title":"Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability","date":"2025-06-04","arxiv_id":"2506.03655","n_code_links":0,"syntology":null},{"paper":"/paper/think-like-a-person-before-responding-a-multi","slug":"think-like-a-person-before-responding-a-multi","title":"Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate","date":"2025-06-04","arxiv_id":"2506.04043","n_code_links":1,"syntology":null},{"paper":"/paper/bitbypass-a-new-direction-in-jailbreaking","slug":"bitbypass-a-new-direction-in-jailbreaking","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","date":"2025-06-03","arxiv_id":"2506.02479","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-effects-of-data-contamination","title":"Rethinking the effects of data contamination in Code Intelligence","date":"2025-06-03","arxiv_id":"2506.02791","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-reasoning-potential-of-pre","title":"Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem","date":"2025-06-03","arxiv_id":"2506.03295","n_code_links":0,"syntology":null},{"paper":null,"slug":"weightlora-keep-only-necessary-adapters","title":"WeightLoRA: Keep Only Necessary Adapters","date":"2025-06-03","arxiv_id":"2506.02724","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-based-model-fingerprinting-for-llm","title":"Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification","date":"2025-06-02","arxiv_id":"2506.01631","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-29","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","date":"2025-06-01","arxiv_id":"2506.00955","n_code_links":0,"syntology":null},{"paper":"/paper/defenderbench-a-toolkit-for-evaluating","slug":"defenderbench-a-toolkit-for-evaluating","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","date":"2025-05-31","arxiv_id":"2506.00739","n_code_links":1,"syntology":null},{"paper":null,"slug":"machine-vs-machine-using-ai-to-tackle","title":"Machine vs Machine: Using AI to Tackle Generative AI Threats in Assessment","date":"2025-05-31","arxiv_id":"2506.02046","n_code_links":0,"syntology":null},{"paper":"/paper/massively-multilingual-adaptation-of-large","slug":"massively-multilingual-adaptation-of-large","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","date":"2025-05-31","arxiv_id":"2506.00469","n_code_links":1,"syntology":null},{"paper":"/paper/mirror-cognitive-inner-monologue-between","slug":"mirror-cognitive-inner-monologue-between","title":"MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs","date":"2025-05-31","arxiv_id":"2506.00430","n_code_links":1,"syntology":null},{"paper":"/paper/helm-hyperbolic-large-language-models-via","slug":"helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","arxiv_id":"2505.24722","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["graph-and-geometric-learning/helm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-are-locally-linear","slug":"large-language-models-are-locally-linear","title":"Large Language Models are Locally Linear Mappings","date":"2025-05-30","arxiv_id":"2505.24293","n_code_links":1,"syntology":null},{"paper":"/paper/the-hallucination-dilemma-factuality-aware","slug":"the-hallucination-dilemma-factuality-aware","title":"The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models","date":"2025-05-30","arxiv_id":"2505.24630","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nusnlp/fspo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/trident-enhancing-large-language-model-safety","slug":"trident-enhancing-large-language-model-safety","title":"TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis","date":"2025-05-30","arxiv_id":"2505.24672","n_code_links":1,"syntology":null},{"paper":"/paper/d-ar-diffusion-via-autoregressive-models","slug":"d-ar-diffusion-via-autoregressive-models","title":"D-AR: Diffusion via Autoregressive Models","date":"2025-05-29","arxiv_id":"2505.23660","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":8,"n_instrument":3,"unverified":3,"pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["showlab/d-ar"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-llm-based-code-generation-with","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","date":"2025-05-29","arxiv_id":"2505.23953","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-regulate-a-new-event-level","title":"Learning to Regulate: A New Event-Level Dataset of Capital Control Measures","date":"2025-05-29","arxiv_id":"2505.23025","n_code_links":0,"syntology":null},{"paper":"/paper/leave-it-to-the-specialist-repair-sparse-llms","slug":"leave-it-to-the-specialist-repair-sparse-llms","title":"Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution","date":"2025-05-29","arxiv_id":"2505.24037","n_code_links":1,"syntology":null},{"paper":null,"slug":"llama-xr-a-novel-framework-for-radiology","title":"LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning","date":"2025-05-29","arxiv_id":"2506.03178","n_code_links":0,"syntology":null},{"paper":null,"slug":"lumion-fast-fault-recovery-for-ml-jobs-using","title":"LUMION: Fast Fault Recovery for ML Jobs Using Programmable Optical Fabrics","date":"2025-05-29","arxiv_id":"2505.23105","n_code_links":0,"syntology":null},{"paper":"/paper/synthetic-document-question-answering-in","slug":"synthetic-document-question-answering-in","title":"Synthetic Document Question Answering in Hungarian","date":"2025-05-29","arxiv_id":"2505.23008","n_code_links":1,"syntology":null},{"paper":null,"slug":"flexible-tool-selection-through-low","title":"Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language","date":"2025-05-28","arxiv_id":"2505.22146","n_code_links":0,"syntology":null},{"paper":null,"slug":"slimllm-accurate-structured-pruning-for-large","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","date":"2025-05-28","arxiv_id":"2505.22689","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-supported-platform-for-system-monitoring","title":"AI-Supported Platform for System Monitoring and Decision-Making in Nuclear Waste Management with Large Language Models","date":"2025-05-27","arxiv_id":"2505.21741","n_code_links":0,"syntology":null},{"paper":null,"slug":"dissecting-physics-reasoning-in-small","title":"Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective","date":"2025-05-27","arxiv_id":"2505.20707","n_code_links":0,"syntology":null},{"paper":null,"slug":"caseedit-enhancing-localized-commonsense","title":"CaseEdit: Enhancing Localized Commonsense Reasoning via Null-Space Constrained Knowledge Editing in Small Parameter Language Models","date":"2025-05-26","arxiv_id":"2505.19383","n_code_links":0,"syntology":null},{"paper":null,"slug":"dcg-sql-enhancing-in-context-learning-for","title":"DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph","date":"2025-05-26","arxiv_id":"2505.19956","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-multilingual-math-reasoning-for","title":"Improving Multilingual Math Reasoning for African Languages","date":"2025-05-26","arxiv_id":"2505.19848","n_code_links":0,"syntology":null},{"paper":null,"slug":"inconsistent-tokenizations-cause-language","title":"Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar","date":"2025-05-26","arxiv_id":"2505.19599","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai4math-a-native-spanish-benchmark-for","title":"AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models","date":"2025-05-25","arxiv_id":"2505.18978","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-data-selection-at-scale-via","title":"Efficient Data Selection at Scale via Influence Distillation","date":"2025-05-25","arxiv_id":"2505.19051","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-ai-for-finance-is-ai-credible-at","title":"Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk?","date":"2025-05-25","arxiv_id":"2505.18953","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-workload-aware-llm-serving-via","title":"Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing","date":"2025-05-24","arxiv_id":"2506.02006","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-do-managers-non-responses-during-earnings","title":"How do managers' non-responses during earnings calls affect analyst forecasts","date":"2025-05-23","arxiv_id":"2505.18419","n_code_links":0,"syntology":null},{"paper":"/paper/neuqi-near-optimal-uniform-quantization","slug":"neuqi-near-optimal-uniform-quantization","title":"NeUQI: Near-Optimal Uniform Quantization Parameter Initialization","date":"2025-05-23","arxiv_id":"2505.17595","n_code_links":1,"syntology":{"ran":6,"of":20,"n_ran_checked":3,"n_instrument":3,"unverified":14,"pointer_only":20,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 14 unverified","official":{"repos":["efsotr/NeUQI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":14,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llamas-have-feelings-too-unveiling-sentiment","title":"LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing","date":"2025-05-22","arxiv_id":"2505.16491","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-safety-detectors-aren-t-enough-a","title":"When Safety Detectors Aren't Enough: A Stealthy and Effective Jailbreak Attack on LLMs via Steganographic Techniques","date":"2025-05-22","arxiv_id":"2505.16765","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-vs-human-judgment-of-content-moderation","title":"AI vs. Human Judgment of Content Moderation: LLM-as-a-Judge and Ethics-Based Response Refusals","date":"2025-05-21","arxiv_id":"2505.15365","n_code_links":0,"syntology":null},{"paper":null,"slug":"aug2search-enhancing-facebook-marketplace","title":"Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation","date":"2025-05-21","arxiv_id":"2505.16065","n_code_links":0,"syntology":null},{"paper":"/paper/chartcards-a-chart-metadata-generation","slug":"chartcards-a-chart-metadata-generation","title":"ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding","date":"2025-05-21","arxiv_id":"2505.15046","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-rank-chain-of-thought-an-energy","title":"Learning to Rank Chain-of-Thought: An Energy-Based Approach with Outcome Supervision","date":"2025-05-21","arxiv_id":"2505.14999","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-prompting-for-improving-llm","title":"Multilingual Prompting for Improving LLM Generation Diversity","date":"2025-05-21","arxiv_id":"2505.15229","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-language-models-in-the-real-world","title":"Small Language Models in the Real World: Insights from Industrial Text Classification","date":"2025-05-21","arxiv_id":"2505.16078","n_code_links":0,"syntology":null},{"paper":null,"slug":"choosing-a-model-shaping-a-future-comparing","title":"Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI","date":"2025-05-20","arxiv_id":"2505.14435","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-use-their-depth","slug":"do-language-models-use-their-depth","title":"Do Language Models Use Their Depth Efficiently?","date":"2025-05-20","arxiv_id":"2505.13898","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["robertcsordas/llm_effective_depth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"temporal-alignment-of-time-sensitive-facts","title":"Temporal Alignment of Time Sensitive Facts with Activation Engineering","date":"2025-05-20","arxiv_id":"2505.14158","n_code_links":0,"syntology":null},{"paper":null,"slug":"a3-an-analytical-low-rank-approximation","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","date":"2025-05-19","arxiv_id":"2505.12942","n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-head-gating-a-framework-for","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","date":"2025-05-19","arxiv_id":"2505.13737","n_code_links":0,"syntology":null},{"paper":"/paper/krikri-advancing-open-large-language-models","slug":"krikri-advancing-open-large-language-models","title":"Krikri: Advancing Open Large Language Models for Greek","date":"2025-05-19","arxiv_id":"2505.13772","n_code_links":0,"syntology":null},{"paper":"/paper/shadow-ft-tuning-instruct-via-base","slug":"shadow-ft-tuning-instruct-via-base","title":"Shadow-FT: Tuning Instruct via Base","date":"2025-05-19","arxiv_id":"2505.12716","n_code_links":1,"syntology":null},{"paper":null,"slug":"extracting-memorized-pieces-of-copyrighted","title":"Extracting memorized pieces of (copyrighted) books from open-weight language models","date":"2025-05-18","arxiv_id":"2505.12546","n_code_links":0,"syntology":null},{"paper":null,"slug":"kvmix-gradient-based-layer-importance-aware","title":"KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache","date":"2025-05-18","arxiv_id":"2506.08018","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-fairness-in-llms-through-testing","title":"Improving Fairness in LLMs Through Testing-Time Adversaries","date":"2025-05-17","arxiv_id":"2505.12100","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-affinity-a-predictive-antibody-antigen","title":"Llama-Affinity: A Predictive Antibody Antigen Binding Model Integrating Antibody Sequences with Llama3 Backbone Architecture","date":"2025-05-17","arxiv_id":"2506.09052","n_code_links":0,"syntology":null},{"paper":"/paper/2505-10833","slug":"2505-10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","date":"2025-05-16","arxiv_id":"2505.10833","n_code_links":1,"syntology":null},{"paper":"/paper/2505-11189","slug":"2505-11189","title":"Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP","date":"2025-05-16","arxiv_id":"2505.11189","n_code_links":1,"syntology":null},{"paper":"/paper/peerguard-defending-multi-agent-systems","slug":"peerguard-defending-multi-agent-systems","title":"PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning","date":"2025-05-16","arxiv_id":"2505.11642","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1062,"with_a_code_link":423,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1062,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":115,"every_run_a_failure_of_syntologys_instrument":28,"listed_with_a_run_with_no_instrument_failure":115,"listed_every_run_a_failure_of_syntologys_instrument":28,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":143,"papers_where_code_ran_first_page":"/method/llama/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":11,"url":"/method/llama/papers/2","json":"/method/llama/papers/2.json","rows":100},{"order":"archive","page":3,"of":11,"url":"/method/llama/papers/3","json":"/method/llama/papers/3.json","rows":100},{"order":"archive","page":4,"of":11,"url":"/method/llama/papers/4","json":"/method/llama/papers/4.json","rows":100},{"order":"archive","page":5,"of":11,"url":"/method/llama/papers/5","json":"/method/llama/papers/5.json","rows":100},{"order":"archive","page":6,"of":11,"url":"/method/llama/papers/6","json":"/method/llama/papers/6.json","rows":100},{"order":"archive","page":7,"of":11,"url":"/method/llama/papers/7","json":"/method/llama/papers/7.json","rows":100},{"order":"archive","page":8,"of":11,"url":"/method/llama/papers/8","json":"/method/llama/papers/8.json","rows":100},{"order":"archive","page":9,"of":11,"url":"/method/llama/papers/9","json":"/method/llama/papers/9.json","rows":100},{"order":"archive","page":10,"of":11,"url":"/method/llama/papers/10","json":"/method/llama/papers/10.json","rows":100},{"order":"archive","page":11,"of":11,"url":"/method/llama/papers/11","json":"/method/llama/papers/11.json","rows":62},{"order":"ran","page":1,"of":2,"url":"/method/llama/papers/ran/1","json":"/method/llama/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/method/llama/papers/ran/2","json":"/method/llama/papers/ran/2.json","rows":43}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":158},{"task":"/task/language-modeling","name":"Language Modeling","papers":135},{"task":"/task/large-language-model","name":"Large Language Model","papers":115},{"task":"/task/question-answering","name":"Question Answering","papers":66},{"task":"/task/quantization","name":"Quantization","papers":62},{"task":null,"name":"GPU","papers":48},{"task":"/task/retrieval","name":"Retrieval","papers":46},{"task":"/task/rag","name":"RAG","papers":45},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":39},{"task":"/task/text-generation","name":"Text Generation","papers":39},{"task":"/task/code-generation","name":"Code Generation","papers":36},{"task":"/task/benchmarking","name":"Benchmarking","papers":34},{"task":"/task/math","name":"Math","papers":34},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":33},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":32},{"task":"/task/decision-making","name":"Decision Making","papers":28},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":28},{"task":"/task/instruction-following","name":"Instruction Following","papers":27},{"task":"/task/mmlu","name":"MMLU","papers":25},{"task":"/task/decoder","name":"Decoder","papers":24}],"tasks_shown":20,"n_tasks":450,"usage_by_year":[{"year":"2023","papers":30},{"year":"2024","papers":640},{"year":"2025","papers":392}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/llama"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=LLaMA","read_at":"2026-10-05T00:58:37+00:00","query":"LLaMA","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"LLaMA","origin_arxiv_id":"2302.13971"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2302.13971","repositories":{"listed":5,"in_graph":56,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2302.13971","citations":21390},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'LLaMA'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[{"name":"LLaMA-Omni","relation":"shares_name_tokens","relation_means":"shares name tokens with this name; a different method","level":3,"retrieve_with":"get_reference_implementation(name='LLaMA-Omni')","origin_arxiv_id":"2409.06666"}],"code_nearby_caption":"Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.","origin_paper":{"arxiv_id":"2302.13971","page":"/paper/llama-open-and-efficient-foundation-language-1","syntology_url":"https://syntology.ai/paper/2302.13971","in_graph_layer":true,"samples":58,"ran":37,"n_ran_checked":25,"n_instrument":12,"unverified":21,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 56 in the graph, strongest link: official). This answer is about arXiv:2302.13971, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"e4449c89fbdbf5bb74da14262379207f873405949bc13fbff69e44dfc68b3af0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}