{"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/gpt-3","slug":"gpt-3","name":"GPT-3","full_name":"GPT-3","full_name_withheld":false,"description_markdown":"**GPT-3** is an autoregressive [transformer](https://paperswithcode.com/methods/category/transformers)  model with 175 billion\r\nparameters. It uses the same architecture/model as [GPT-2](https://paperswithcode.com/method/gpt-2), including the modified initialization, pre-normalization, and reversible tokenization, with the exception that GPT-3 uses alternating dense and locally banded sparse attention patterns in the layers of the [transformer](https://paperswithcode.com/method/transformer), similar to the [Sparse Transformer](https://paperswithcode.com/method/sparse-transformer).","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2005.14165v4","title":"Language Models are Few-Shot Learners","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/EleutherAI/gpt-neox","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":1906,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"2506-10330","title":"Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements","date":"2025-06-12","arxiv_id":"2506.10330","n_code_links":0,"syntology":null},{"paper":"/paper/think-before-you-simulate-symbolic-reasoning-1","slug":"think-before-you-simulate-symbolic-reasoning-1","title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","date":"2025-06-12","arxiv_id":"2506.10753","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-hate-speech-detection-in-social","title":"Multilingual Hate Speech Detection in Social Media Using Translation-Based Approaches with Large Language Models","date":"2025-06-09","arxiv_id":"2506.08147","n_code_links":0,"syntology":null},{"paper":null,"slug":"direct-behavior-optimization-unlocking-the","title":"Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs","date":"2025-06-06","arxiv_id":"2506.06401","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":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":"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":null,"slug":"finbert2-a-specialized-bidirectional-encoder","title":"FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models","date":"2025-05-31","arxiv_id":"2506.06335","n_code_links":0,"syntology":null},{"paper":null,"slug":"critical-batch-size-revisited-a-simple","title":"Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training","date":"2025-05-29","arxiv_id":"2505.23971","n_code_links":0,"syntology":null},{"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":"say-what-you-mean-natural-language-access","title":"Say What You Mean: Natural Language Access Control with Large Language Models for Internet of Things","date":"2025-05-28","arxiv_id":"2505.23835","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversational-lexicography-querying","title":"Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language","date":"2025-05-26","arxiv_id":"2505.19971","n_code_links":0,"syntology":null},{"paper":"/paper/generative-ai-and-creativity-a-systematic","slug":"generative-ai-and-creativity-a-systematic","title":"Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis","date":"2025-05-22","arxiv_id":"2505.17241","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-testing-in-llms-insights-into","title":"Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities","date":"2025-05-19","arxiv_id":"2505.13195","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-at-detecting","title":"Are Large Language Models Good at Detecting Propaganda?","date":"2025-05-19","arxiv_id":"2505.13706","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaloop-assessing-llm-robustness-in","title":"EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective","date":"2025-05-18","arxiv_id":"2505.12185","n_code_links":0,"syntology":null},{"paper":null,"slug":"let-the-trial-begin-a-mock-court-approach-to","title":"Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents","date":"2025-05-16","arxiv_id":"2505.10961","n_code_links":0,"syntology":null},{"paper":"/paper/comparing-llm-text-annotation-skills-a-study","slug":"comparing-llm-text-annotation-skills-a-study","title":"Comparing LLM Text Annotation Skills: A Study on Human Rights Violations in Social Media Data","date":"2025-05-15","arxiv_id":"2505.10260","n_code_links":1,"syntology":null},{"paper":"/paper/achieving-scalable-robot-autonomy-via","slug":"achieving-scalable-robot-autonomy-via","title":"Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM","date":"2025-05-13","arxiv_id":"2505.08492","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-black-box","title":"Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow","date":"2025-05-13","arxiv_id":"2505.08303","n_code_links":0,"syntology":null},{"paper":"/paper/healthbench-evaluating-large-language-models","slug":"healthbench-evaluating-large-language-models","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","date":"2025-05-13","arxiv_id":"2505.08775","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/simple-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/grada-graph-based-reranker-against","slug":"grada-graph-based-reranker-against","title":"GRADA: Graph-based Reranker against Adversarial Documents Attack","date":"2025-05-12","arxiv_id":"2505.07546","n_code_links":1,"syntology":null},{"paper":null,"slug":"refine-af-a-task-agnostic-framework-to-align","title":"REFINE-AF: A Task-Agnostic Framework to Align Language Models via Self-Generated Instructions using Reinforcement Learning from Automated Feedback","date":"2025-05-10","arxiv_id":"2505.06548","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empathic-gpt-based-chatbot-to-talk-about","title":"An empathic GPT-based chatbot to talk about mental disorders with Spanish teenagers","date":"2025-05-09","arxiv_id":"2505.05828","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-is-next-for-llms-next-generation-ai","title":"What Is Next for LLMs? Next-Generation AI Computing Hardware Using Photonic Chips","date":"2025-05-09","arxiv_id":"2505.05794","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-large-language-1","title":"Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarization","date":"2025-05-08","arxiv_id":"2505.05070","n_code_links":0,"syntology":null},{"paper":null,"slug":"bringing-legal-knowledge-to-the-public-by","title":"Bringing legal knowledge to the public by constructing a legal question bank using large-scale pre-trained language model","date":"2025-05-07","arxiv_id":"2505.04132","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-domain-adaptation-of-large-language-models","title":"A Domain Adaptation of Large Language Models for Classifying Mechanical Assembly Components","date":"2025-05-02","arxiv_id":"2505.01627","n_code_links":0,"syntology":null},{"paper":null,"slug":"jaccdiv-a-metric-and-benchmark-for","title":"JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry","date":"2025-04-29","arxiv_id":"2504.20849","n_code_links":0,"syntology":null},{"paper":null,"slug":"veridebug-a-unified-llm-for-verilog-debugging","title":"VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction","date":"2025-04-27","arxiv_id":"2504.19099","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-you-shouldn-t-fully-trust-chatgpt-a","title":"Why you shouldn't fully trust ChatGPT: A synthesis of this AI tool's error rates across disciplines and the software engineering lifecycle","date":"2025-04-26","arxiv_id":"2504.18858","n_code_links":0,"syntology":null},{"paper":null,"slug":"amplified-vulnerabilities-structured","title":"Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate","date":"2025-04-23","arxiv_id":"2504.16489","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-sensitivity-evaluation-framework-for","title":"LLM Sensitivity Evaluation Framework for Clinical Diagnosis","date":"2025-04-18","arxiv_id":"2504.13475","n_code_links":0,"syntology":null},{"paper":null,"slug":"validating-llm-generated-relevance-labels-for","title":"Validating LLM-Generated Relevance Labels for Educational Resource Search","date":"2025-04-17","arxiv_id":"2504.12732","n_code_links":0,"syntology":null},{"paper":null,"slug":"vexp-a-low-cost-risc-v-isa-extension-for","title":"VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in Transformers","date":"2025-04-15","arxiv_id":"2504.11227","n_code_links":0,"syntology":null},{"paper":null,"slug":"lumos-efficient-performance-modeling-and","title":"Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training","date":"2025-04-12","arxiv_id":"2504.09307","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-elders-making-an-llm-powered","title":"Learning from Elders: Making an LLM-powered Chatbot for Retirement Communities more Accessible through User-centered Design","date":"2025-04-11","arxiv_id":"2504.08985","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-for-comparative-narrative-analysis","title":"LLM for Comparative Narrative Analysis","date":"2025-04-11","arxiv_id":"2504.08211","n_code_links":0,"syntology":null},{"paper":null,"slug":"pogo-a-scalable-proof-of-useful-work-via","title":"PoGO: A Scalable Proof of Useful Work via Quantized Gradient Descent and Merkle Proofs","date":"2025-04-10","arxiv_id":"2504.07540","n_code_links":0,"syntology":null},{"paper":"/paper/weak-for-strong-training-weak-meta-agent-to","slug":"weak-for-strong-training-weak-meta-agent-to","title":"Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors","date":"2025-04-07","arxiv_id":"2504.04785","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-dynamic-clustering-based-document","slug":"efficient-dynamic-clustering-based-document","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","date":"2025-04-04","arxiv_id":"2504.03165","n_code_links":1,"syntology":null},{"paper":"/paper/task-as-context-prompting-for-accurate","slug":"task-as-context-prompting-for-accurate","title":"Task as Context Prompting for Accurate Medical Symptom Coding Using Large Language Models","date":"2025-04-03","arxiv_id":"2504.03051","n_code_links":1,"syntology":null},{"paper":null,"slug":"onrl-rag-real-time-personalized-mental-health","title":"OnRL-RAG: Real-Time Personalized Mental Health Dialogue System","date":"2025-04-02","arxiv_id":"2504.02894","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategize-globally-adapt-locally-a-multi","title":"Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning","date":"2025-04-02","arxiv_id":"2504.01278","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-reasoning-with-large-language-models","title":"Does \"Reasoning\" with Large Language Models Improve Recognizing, Generating, and Reframing Unhelpful Thoughts?","date":"2025-03-31","arxiv_id":"2504.00163","n_code_links":0,"syntology":null},{"paper":null,"slug":"rubric-is-all-you-need-enhancing-llm-based","title":"Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics","date":"2025-03-31","arxiv_id":"2503.23989","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-detection-designing-ai-resilient","title":"Beyond Detection: Designing AI-Resilient Assessments with Automated Feedback Tool to Foster Critical Thinking","date":"2025-03-30","arxiv_id":"2503.23622","n_code_links":0,"syntology":null},{"paper":"/paper/lavic-adapting-large-vision-language-models","slug":"lavic-adapting-large-vision-language-models","title":"LaViC: Adapting Large Vision-Language Models to Visually-Aware Conversational Recommendation","date":"2025-03-30","arxiv_id":"2503.23312","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-training-free-llm-framework-with","title":"A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks","date":"2025-03-29","arxiv_id":"2503.23053","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-artificial-intelligence-with","title":"Integrating Artificial Intelligence with Human Expertise: An In-depth Analysis of ChatGPT's Capabilities in Generating Metamorphic Relations","date":"2025-03-28","arxiv_id":"2503.22141","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-llms-for-predicting-unknown","title":"Leveraging LLMs for Predicting Unknown Diagnoses from Clinical Notes","date":"2025-03-28","arxiv_id":"2503.22092","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-evaluation-of-llms-and-google-translate","title":"An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses","date":"2025-03-27","arxiv_id":"2503.21393","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-we-make-code-green-understanding-trade","title":"Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations","date":"2025-03-26","arxiv_id":"2503.20126","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-prompting-with-persuasion-skills-in","title":"Iterative Prompting with Persuasion Skills in Jailbreaking Large Language Models","date":"2025-03-26","arxiv_id":"2503.20320","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-recent-large-language-models","title":"Investigating Recent Large Language Models for Vietnamese Machine Reading Comprehension","date":"2025-03-23","arxiv_id":"2503.18062","n_code_links":0,"syntology":null},{"paper":null,"slug":"unify-and-triumph-polyglot-diverse-and-self","title":"Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs","date":"2025-03-20","arxiv_id":"2503.16144","n_code_links":0,"syntology":null},{"paper":"/paper/burtorch-revisiting-training-from-first","slug":"burtorch-revisiting-training-from-first","title":"BurTorch: Revisiting Training from First Principles by Coupling Autodiff, Math Optimization, and Systems","date":"2025-03-18","arxiv_id":"2503.13795","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-chain-of-thought-and-retrieval","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","date":"2025-03-15","arxiv_id":"2503.12286","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-subspace-representation-fine","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","date":"2025-03-13","arxiv_id":"2503.10617","n_code_links":0,"syntology":null},{"paper":null,"slug":"it-is-too-many-options-pitfalls-of-multiple","title":"It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education","date":"2025-03-13","arxiv_id":"2503.13508","n_code_links":0,"syntology":null},{"paper":null,"slug":"siege-autonomous-multi-turn-jailbreaking-of","title":"Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search","date":"2025-03-13","arxiv_id":"2503.10619","n_code_links":0,"syntology":null},{"paper":null,"slug":"vaxguard-a-multi-generator-multi-type-and","title":"VaxGuard: A Multi-Generator, Multi-Type, and Multi-Role Dataset for Detecting LLM-Generated Vaccine Misinformation","date":"2025-03-12","arxiv_id":"2503.09103","n_code_links":0,"syntology":null},{"paper":"/paper/context-aware-biases-for-length-extrapolation","slug":"context-aware-biases-for-length-extrapolation","title":"Context-aware Biases for Length Extrapolation","date":"2025-03-11","arxiv_id":"2503.08067","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["axiomlab/Cable"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"llms-virtual-users-and-bias-predicting-any","title":"Llms, Virtual Users, and Bias: Predicting Any Survey Question Without Human Data","date":"2025-03-11","arxiv_id":"2503.16498","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-multimodal-perception-in-large","title":"Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings","date":"2025-03-10","arxiv_id":"2503.06980","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-autonomous-programming-using-iterative","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","date":"2025-03-10","arxiv_id":"2503.07693","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-zero-shot-cot-in-japanese","title":"Effectiveness of Zero-shot-CoT in Japanese Prompts","date":"2025-03-09","arxiv_id":"2503.06765","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-local-and-cloud-based-large","title":"Simulating and Analysing Human Survey Responses with Large Language Models: A Case Study in Energy Stated Preference","date":"2025-03-07","arxiv_id":"2503.10652","n_code_links":0,"syntology":null},{"paper":null,"slug":"hilgen-hierarchically-informed-data","title":"HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models","date":"2025-03-06","arxiv_id":"2503.04930","n_code_links":0,"syntology":null},{"paper":null,"slug":"use-me-wisely-ai-driven-assessment-for-llm","title":"Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development","date":"2025-03-04","arxiv_id":"2503.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"psychological-counseling-ability-of-large","title":"Psychological Counseling Ability of Large Language Models","date":"2025-03-01","arxiv_id":"2503.07627","n_code_links":0,"syntology":null},{"paper":"/paper/nutrigen-personalized-meal-plan-generator","slug":"nutrigen-personalized-meal-plan-generator","title":"NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence","date":"2025-02-28","arxiv_id":"2502.20601","n_code_links":1,"syntology":null},{"paper":null,"slug":"cognitive-networks-highlight-differences-and","title":"Cognitive networks highlight differences and similarities in the STEM mindsets of human and LLM-simulated trainees, experts and academics","date":"2025-02-26","arxiv_id":"2502.19529","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-in-agentic","title":"Assessing Large Language Models in Agentic Multilingual National Bias","date":"2025-02-25","arxiv_id":"2502.17945","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-about-affordances-causal-and","title":"Reasoning about Affordances: Causal and Compositional Reasoning in LLMs","date":"2025-02-23","arxiv_id":"2502.16606","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-pass-detection-of-jailbreaking-input","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","date":"2025-02-21","arxiv_id":"2502.15435","n_code_links":0,"syntology":null},{"paper":null,"slug":"rgar-recurrence-generation-augmented","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","date":"2025-02-19","arxiv_id":"2502.13361","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-llm-powered-agent-for-physiological-data","title":"An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation","date":"2025-02-18","arxiv_id":"2502.12836","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartllm-smart-contract-auditing-using-custom","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","date":"2025-02-17","arxiv_id":"2502.13167","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","n_code_links":0,"syntology":null},{"paper":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-reason-causally-like","title":"Do Large Language Models Reason Causally Like Us? Even Better?","date":"2025-02-14","arxiv_id":"2502.10215","n_code_links":0,"syntology":null},{"paper":"/paper/grammar-control-in-dialogue-response","slug":"grammar-control-in-dialogue-response","title":"Grammar Control in Dialogue Response Generation for Language Learning Chatbots","date":"2025-02-11","arxiv_id":"2502.07544","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-prompt-engineering-techniques","title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","date":"2025-02-09","arxiv_id":"2502.06039","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-in-file","title":"Large Language Models for In-File Vulnerability Localization Can Be \"Lost in the End\"","date":"2025-02-09","arxiv_id":"2502.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"forbidden-science-dual-use-ai-challenge","title":"Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests","date":"2025-02-08","arxiv_id":"2502.06867","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-understand-1","title":"Can Large Language Models Understand Intermediate Representations?","date":"2025-02-07","arxiv_id":"2502.06854","n_code_links":0,"syntology":null},{"paper":null,"slug":"psyplay-personality-infused-role-playing","title":"PsyPlay: Personality-Infused Role-Playing Conversational Agents","date":"2025-02-06","arxiv_id":"2502.03821","n_code_links":0,"syntology":null},{"paper":"/paper/codesteer-symbolic-augmented-language-models","slug":"codesteer-symbolic-augmented-language-models","title":"CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance","date":"2025-02-04","arxiv_id":"2502.04350","n_code_links":1,"syntology":null},{"paper":null,"slug":"coddllm-empowering-large-language-models-for","title":"CoddLLM: Empowering Large Language Models for Data Analytics","date":"2025-02-01","arxiv_id":"2502.00329","n_code_links":0,"syntology":null},{"paper":"/paper/kbqa-o1-agentic-knowledge-base-question","slug":"kbqa-o1-agentic-knowledge-base-question","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","date":"2025-01-31","arxiv_id":"2501.18922","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["lhrlab/kbqa-o1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-accuracy-in-emulating","title":"Large Language Models' Accuracy in Emulating Human Experts' Evaluation of Public Sentiments about Heated Tobacco Products on Social Media","date":"2025-01-31","arxiv_id":"2502.01658","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-embedding-vs-task-specific-embedding","title":"General Embedding vs. Task-Specific Embedding: A Comparative Approach to Enhancing NLP Performance","date":"2025-01-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/unraveling-the-capabilities-of-language","slug":"unraveling-the-capabilities-of-language","title":"Unraveling the Capabilities of Language Models in News Summarization","date":"2025-01-30","arxiv_id":"2501.18128","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-graphs-for-table-and-text-based","title":"Hybrid Graphs for Table-and-Text based Question Answering using LLMs","date":"2025-01-29","arxiv_id":"2501.17767","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-attacks-with-pruning-optimizing","slug":"graph-of-attacks-with-pruning-optimizing","title":"Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation","date":"2025-01-28","arxiv_id":"2501.18638","n_code_links":1,"syntology":null},{"paper":"/paper/an-ai-driven-live-systematic-reviews-in-the","slug":"an-ai-driven-live-systematic-reviews-in-the","title":"An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis","date":"2025-01-25","arxiv_id":"2501.17181","n_code_links":1,"syntology":null},{"paper":"/paper/speech-translation-refinement-using-large","slug":"speech-translation-refinement-using-large","title":"Speech Translation Refinement using Large Language Models","date":"2025-01-25","arxiv_id":"2501.15090","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-based-cost-effective-evaluation-and","title":"Prompt-Based Cost-Effective Evaluation and Operation of ChatGPT as a Computer Programming Teaching Assistant","date":"2025-01-24","arxiv_id":"2501.17176","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-table-instruction-tuning","slug":"rethinking-table-instruction-tuning","title":"Rethinking Table Instruction Tuning","date":"2025-01-24","arxiv_id":"2501.14693","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1906,"with_a_code_link":866,"where_syntology_ran_a_sample":319,"not_listed_spam_title":0,"listed":1906,"listed_where_code_ran":319,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":248,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":248,"listed_every_run_a_failure_of_syntologys_instrument":71,"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":319,"papers_where_code_ran_first_page":"/method/gpt-3/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":20,"url":"/method/gpt-3/papers/2","json":"/method/gpt-3/papers/2.json","rows":100},{"order":"archive","page":3,"of":20,"url":"/method/gpt-3/papers/3","json":"/method/gpt-3/papers/3.json","rows":100},{"order":"archive","page":4,"of":20,"url":"/method/gpt-3/papers/4","json":"/method/gpt-3/papers/4.json","rows":100},{"order":"archive","page":5,"of":20,"url":"/method/gpt-3/papers/5","json":"/method/gpt-3/papers/5.json","rows":100},{"order":"archive","page":6,"of":20,"url":"/method/gpt-3/papers/6","json":"/method/gpt-3/papers/6.json","rows":100},{"order":"archive","page":7,"of":20,"url":"/method/gpt-3/papers/7","json":"/method/gpt-3/papers/7.json","rows":100},{"order":"archive","page":8,"of":20,"url":"/method/gpt-3/papers/8","json":"/method/gpt-3/papers/8.json","rows":100},{"order":"archive","page":9,"of":20,"url":"/method/gpt-3/papers/9","json":"/method/gpt-3/papers/9.json","rows":100},{"order":"archive","page":10,"of":20,"url":"/method/gpt-3/papers/10","json":"/method/gpt-3/papers/10.json","rows":100},{"order":"archive","page":11,"of":20,"url":"/method/gpt-3/papers/11","json":"/method/gpt-3/papers/11.json","rows":100},{"order":"archive","page":12,"of":20,"url":"/method/gpt-3/papers/12","json":"/method/gpt-3/papers/12.json","rows":100},{"order":"archive","page":13,"of":20,"url":"/method/gpt-3/papers/13","json":"/method/gpt-3/papers/13.json","rows":100},{"order":"archive","page":14,"of":20,"url":"/method/gpt-3/papers/14","json":"/method/gpt-3/papers/14.json","rows":100},{"order":"archive","page":15,"of":20,"url":"/method/gpt-3/papers/15","json":"/method/gpt-3/papers/15.json","rows":100},{"order":"archive","page":16,"of":20,"url":"/method/gpt-3/papers/16","json":"/method/gpt-3/papers/16.json","rows":100},{"order":"archive","page":17,"of":20,"url":"/method/gpt-3/papers/17","json":"/method/gpt-3/papers/17.json","rows":100},{"order":"archive","page":18,"of":20,"url":"/method/gpt-3/papers/18","json":"/method/gpt-3/papers/18.json","rows":100},{"order":"archive","page":19,"of":20,"url":"/method/gpt-3/papers/19","json":"/method/gpt-3/papers/19.json","rows":100},{"order":"archive","page":20,"of":20,"url":"/method/gpt-3/papers/20","json":"/method/gpt-3/papers/20.json","rows":6},{"order":"ran","page":1,"of":4,"url":"/method/gpt-3/papers/ran/1","json":"/method/gpt-3/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":4,"url":"/method/gpt-3/papers/ran/2","json":"/method/gpt-3/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":4,"url":"/method/gpt-3/papers/ran/3","json":"/method/gpt-3/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":4,"url":"/method/gpt-3/papers/ran/4","json":"/method/gpt-3/papers/ran/4.json","rows":19}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":363},{"task":"/task/language-modeling","name":"Language Modeling","papers":265},{"task":"/task/question-answering","name":"Question Answering","papers":206},{"task":"/task/large-language-model","name":"Large Language Model","papers":187},{"task":"/task/retrieval","name":"Retrieval","papers":128},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":115},{"task":"/task/text-generation","name":"Text Generation","papers":103},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":88},{"task":"/task/code-generation","name":"Code Generation","papers":80},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":78},{"task":"/task/sentence","name":"Sentence","papers":75},{"task":"/task/math","name":"Math","papers":61},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":59},{"task":"/task/rag","name":"RAG","papers":58},{"task":"/task/decision-making","name":"Decision Making","papers":54},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":54},{"task":"/task/hallucination","name":"Hallucination","papers":45},{"task":"/task/benchmarking","name":"Benchmarking","papers":43},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":42},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":40}],"tasks_shown":20,"n_tasks":665,"usage_by_year":[{"year":"2020","papers":16},{"year":"2021","papers":99},{"year":"2022","papers":219},{"year":"2023","papers":744},{"year":"2024","papers":716},{"year":"2025","papers":112}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gpt-3"},"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=GPT-3","read_at":"2026-10-05T00:57:09+00:00","query":"GPT-3","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'GPT-3' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["GPT","GPT-D","H-GPT","RF-GPT","MS-GPT","GPT-RE","VA-GPT","GPT-ST"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"a94d311ca13bed1aeec123af1ee4ba7219dcf938783313b2b952e548a09d6e7a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}