{"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/flan-t5","slug":"flan-t5","name":"Flan-T5","full_name":"Flan-T5","full_name_withheld":false,"description_markdown":"**Flan-T5** is the instruction fine-tuned version of **T5** or **Text-to-Text Transfer Transformer** Language Model.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Scaling Instruction-Finetuned Language Models","paper":"/paper/scaling-instruction-finetuned-language-models","first_author":"Hyung Won Chung","n_authors":35,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/scaling-instruction-finetuned-language-models"},"source":{"url":"https://arxiv.org/abs/2210.11416v5","title":"Scaling Instruction-Finetuned 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":107,"archive_num_papers":107,"papers_newest_first":[{"paper":null,"slug":"lilm-rdb-sfc-lightweight-language-model-with","title":"LiLM-RDB-SFC: Lightweight Language Model with Relational Database-Guided DRL for Optimized SFC Provisioning","date":"2025-07-15","arxiv_id":"2507.10903","n_code_links":0,"syntology":null},{"paper":"/paper/value-free-policy-optimization-via-reward","slug":"value-free-policy-optimization-via-reward","title":"Value-Free Policy Optimization via Reward Partitioning","date":"2025-06-16","arxiv_id":"2506.13702","n_code_links":1,"syntology":null},{"paper":"/paper/masking-in-multi-hop-qa-an-analysis-of-how","slug":"masking-in-multi-hop-qa-an-analysis-of-how","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","date":"2025-05-16","arxiv_id":"2505.11754","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-email-spam-detection-leveraging","slug":"advancing-email-spam-detection-leveraging","title":"Advancing Email Spam Detection: Leveraging Zero-Shot Learning and Large Language Models","date":"2025-05-05","arxiv_id":"2505.02362","n_code_links":1,"syntology":null},{"paper":"/paper/ip-crr-information-pursuit-for-interpretable","slug":"ip-crr-information-pursuit-for-interpretable","title":"IP-CRR: Information Pursuit for Interpretable Classification of Chest Radiology Reports","date":"2025-04-30","arxiv_id":"2505.00191","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-moe-based-large-language-model-for","title":"Leveraging MoE-based Large Language Model for Zero-Shot Multi-Task Semantic Communication","date":"2025-03-19","arxiv_id":"2503.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","n_code_links":0,"syntology":null},{"paper":null,"slug":"pay-attention-to-real-world-perturbations","title":"Pay Attention to Real World Perturbations! Natural Robustness Evaluation in Machine Reading Comprehension","date":"2025-02-23","arxiv_id":"2502.16523","n_code_links":0,"syntology":null},{"paper":"/paper/star-spectral-truncation-and-rescale-for","slug":"star-spectral-truncation-and-rescale-for","title":"STAR: Spectral Truncation and Rescale for Model Merging","date":"2025-02-14","arxiv_id":"2502.10339","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ibm/star"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cross-language-approach-for-quranic-qa","title":"Cross-Language Approach for Quranic QA","date":"2025-01-29","arxiv_id":"2501.17449","n_code_links":0,"syntology":null},{"paper":"/paper/flanec-exploring-flan-t5-for-post-asr-error","slug":"flanec-exploring-flan-t5-for-post-asr-error","title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","date":"2025-01-22","arxiv_id":"2501.12979","n_code_links":1,"syntology":null},{"paper":"/paper/label-privacy-in-split-learning-for-large","slug":"label-privacy-in-split-learning-for-large","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","date":"2024-12-21","arxiv_id":"2412.16669","n_code_links":1,"syntology":null},{"paper":null,"slug":"transforming-nlu-with-babylon-a-case-study-in","title":"Transforming NLU with Babylon: A Case Study in Development of Real-time, Edge-Efficient, Multi-Intent Translation System for Automated Drive-Thru Ordering","date":"2024-11-22","arxiv_id":"2411.15372","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-or-a-semblance-of-it-a-diagnostic","title":"Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs","date":"2024-10-26","arxiv_id":"2410.20200","n_code_links":0,"syntology":null},{"paper":null,"slug":"guardians-of-discourse-evaluating-llms-on","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","date":"2024-10-21","arxiv_id":"2410.15623","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-electronic-health-records-text","title":"Enhanced Electronic Health Records Text Summarization Using Large Language Models","date":"2024-10-12","arxiv_id":"2410.09628","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanity-in-ai-detecting-the-personality-of","title":"Humanity in AI: Detecting the Personality of Large Language Models","date":"2024-10-11","arxiv_id":"2410.08545","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-are-graph-learners","title":"How to Make LLMs Strong Node Classifiers?","date":"2024-10-03","arxiv_id":"2410.02296","n_code_links":0,"syntology":null},{"paper":"/paper/crowdcounter-a-benchmark-type-specific-multi","slug":"crowdcounter-a-benchmark-type-specific-multi","title":"CrowdCounter: A benchmark type-specific multi-target counterspeech dataset","date":"2024-10-02","arxiv_id":"2410.01400","n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-aware-response-generation-using","title":"Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation","date":"2024-10-02","arxiv_id":"2410.01306","n_code_links":0,"syntology":null},{"paper":"/paper/taskcomplexity-a-dataset-for-task-complexity","slug":"taskcomplexity-a-dataset-for-task-complexity","title":"TaskComplexity: A Dataset for Task Complexity Classification with In-Context Learning, FLAN-T5 and GPT-4o Benchmarks","date":"2024-09-30","arxiv_id":"2409.20189","n_code_links":1,"syntology":null},{"paper":null,"slug":"mimii-gen-generative-modeling-approach-for","title":"MIMII-Gen: Generative Modeling Approach for Simulated Evaluation of Anomalous Sound Detection System","date":"2024-09-27","arxiv_id":"2409.18542","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-text-representation-learning-via","title":"Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrieval","date":"2024-09-24","arxiv_id":"2409.16497","n_code_links":0,"syntology":null},{"paper":"/paper/cacer-clinical-concept-annotations-for-cancer","slug":"cacer-clinical-concept-annotations-for-cancer","title":"CACER: Clinical Concept Annotations for Cancer Events and Relations","date":"2024-09-05","arxiv_id":"2409.03905","n_code_links":1,"syntology":null},{"paper":null,"slug":"instruction-finetuning-for-leaderboard","title":"Instruction Finetuning for Leaderboard Generation from Empirical AI Research","date":"2024-08-19","arxiv_id":"2408.10141","n_code_links":0,"syntology":null},{"paper":"/paper/smile-zero-shot-sparse-mixture-of-low-rank","slug":"smile-zero-shot-sparse-mixture-of-low-rank","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","date":"2024-08-19","arxiv_id":"2408.10174","n_code_links":1,"syntology":null},{"paper":"/paper/towards-enhancing-coherence-in-extractive","slug":"towards-enhancing-coherence-in-extractive","title":"Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs","date":"2024-07-05","arxiv_id":"2407.04855","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-vs-large-language-models-for","title":"Convolutional vs Large Language Models for Software Log Classification in Edge-Deployable Cellular Network Testing","date":"2024-07-04","arxiv_id":"2407.03759","n_code_links":0,"syntology":null},{"paper":"/paper/deep-content-understanding-toward-entity-and","slug":"deep-content-understanding-toward-entity-and","title":"Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models","date":"2024-07-04","arxiv_id":"2407.04050","n_code_links":1,"syntology":null},{"paper":null,"slug":"factual-dialogue-summarization-via-learning","title":"Factual Dialogue Summarization via Learning from Large Language Models","date":"2024-06-20","arxiv_id":"2406.14709","n_code_links":0,"syntology":null},{"paper":null,"slug":"incremental-comprehension-of-garden-path","title":"Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention","date":"2024-05-25","arxiv_id":"2405.16042","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-spam-email-classification-using-pre","title":"Zero-Shot Spam Email Classification Using Pre-trained Large Language Models","date":"2024-05-24","arxiv_id":"2405.15936","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-sample-specific-encoder","title":"Efficient Sample-Specific Encoder Perturbations","date":"2024-05-01","arxiv_id":"2405.01601","n_code_links":0,"syntology":null},{"paper":"/paper/calc-cmu-at-semeval-2024-task-7-pre-calc","slug":"calc-cmu-at-semeval-2024-task-7-pre-calc","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","date":"2024-04-22","arxiv_id":"2404.14355","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["calc-cmu/pre-calc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-in-targeted-sentiment","slug":"large-language-models-in-targeted-sentiment","title":"Large Language Models in Targeted Sentiment Analysis","date":"2024-04-18","arxiv_id":"2404.12342","n_code_links":2,"syntology":null},{"paper":"/paper/search-beyond-queries-training-smaller","slug":"search-beyond-queries-training-smaller","title":"Grounded Language Agent for Product Search via Intelligent Web Interactions","date":"2024-04-16","arxiv_id":"2404.10887","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["MultifacetedNLP/Web-Agents-Unsupervised"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"language-model-cascades-token-level","title":"Language Model Cascades: Token-level uncertainty and beyond","date":"2024-04-15","arxiv_id":"2404.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"vocabulary-attack-to-hijack-large-language","title":"Vocabulary Attack to Hijack Large Language Model Applications","date":"2024-04-03","arxiv_id":"2404.02637","n_code_links":0,"syntology":null},{"paper":"/paper/flawn-t5-an-empirical-examination-of","slug":"flawn-t5-an-empirical-examination-of","title":"LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain","date":"2024-04-02","arxiv_id":"2404.02127","n_code_links":1,"syntology":null},{"paper":"/paper/illuminer-instruction-tuned-large-language","slug":"illuminer-instruction-tuned-large-language","title":"ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler","date":"2024-03-26","arxiv_id":"2403.17536","n_code_links":1,"syntology":null},{"paper":null,"slug":"masontigers-at-semeval-2024-task-8","title":"MasonTigers at SemEval-2024 Task 8: Performance Analysis of Transformer-based Models on Machine-Generated Text Detection","date":"2024-03-22","arxiv_id":"2403.14989","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-to-extract","title":"Leveraging Large Language Models to Extract Information on Substance Use Disorder Severity from Clinical Notes: A Zero-shot Learning Approach","date":"2024-03-18","arxiv_id":"2403.12297","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-vqa-with-frozen-llms-a-tale-of-two","title":"Few-Shot VQA with Frozen LLMs: A Tale of Two Approaches","date":"2024-03-17","arxiv_id":"2403.11317","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-large-language-model-kg-llm","title":"Knowledge Graph Large Language Model (KG-LLM) for Link Prediction","date":"2024-03-12","arxiv_id":"2403.07311","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-architectural-design","title":"Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study","date":"2024-03-04","arxiv_id":"2403.01709","n_code_links":0,"syntology":null},{"paper":"/paper/formulation-comparison-for-timeline","slug":"formulation-comparison-for-timeline","title":"Formulation Comparison for Timeline Construction using LLMs","date":"2024-03-01","arxiv_id":"2403.00990","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-opt-optimizing-inference-of-large","title":"Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization","date":"2024-02-29","arxiv_id":"2403.00067","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-news-narratives-a-critical-analysis","title":"Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection","date":"2024-02-18","arxiv_id":"2402.11621","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-dimensional-evaluation-of-empathetic","title":"Multi-dimensional Evaluation of Empathetic Dialog Responses","date":"2024-02-18","arxiv_id":"2402.11409","n_code_links":0,"syntology":null},{"paper":"/paper/both-matter-enhancing-the-emotional","slug":"both-matter-enhancing-the-emotional","title":"Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence","date":"2024-02-15","arxiv_id":"2402.10073","n_code_links":1,"syntology":null},{"paper":"/paper/attnlrp-attention-aware-layer-wise-relevance","slug":"attnlrp-attention-aware-layer-wise-relevance","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","date":"2024-02-08","arxiv_id":"2402.05602","n_code_links":2,"syntology":null},{"paper":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","n_code_links":0,"syntology":null},{"paper":"/paper/girt-model-automated-generation-of-issue","slug":"girt-model-automated-generation-of-issue","title":"GIRT-Model: Automated Generation of Issue Report Templates","date":"2024-02-04","arxiv_id":"2402.02632","n_code_links":1,"syntology":null},{"paper":null,"slug":"tiny-titans-can-smaller-large-language-models","title":"Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?","date":"2024-02-01","arxiv_id":"2402.00841","n_code_links":0,"syntology":null},{"paper":null,"slug":"socially-aware-synthetic-data-generation-for","title":"Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models","date":"2024-01-25","arxiv_id":"2402.01712","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-scientific-1","title":"Large Language Models for Scientific Information Extraction: An Empirical Study for Virology","date":"2024-01-18","arxiv_id":"2401.10040","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-emotions-demographic","slug":"learning-from-emotions-demographic","title":"Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues","date":"2024-01-17","arxiv_id":"2401.09248","n_code_links":1,"syntology":null},{"paper":"/paper/nomiracl-knowing-when-you-don-t-know-for","slug":"nomiracl-knowing-when-you-don-t-know-for","title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","date":"2023-12-18","arxiv_id":"2312.11361","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["project-miracl/nomiracl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"novacomet-open-commonsense-foundation-models","title":"NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation","date":"2023-12-10","arxiv_id":"2312.05979","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-filter-context-for-retrieval","slug":"learning-to-filter-context-for-retrieval","title":"Learning to Filter Context for Retrieval-Augmented Generation","date":"2023-11-14","arxiv_id":"2311.08377","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zorazrw/filco"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/extraction-of-atypical-aspects-from-customer","slug":"extraction-of-atypical-aspects-from-customer","title":"Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models","date":"2023-11-05","arxiv_id":"2311.02702","n_code_links":2,"syntology":null},{"paper":"/paper/people-make-better-edits-measuring-the","slug":"people-make-better-edits-measuring-the","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","date":"2023-11-02","arxiv_id":"2311.01270","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 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) · 1 unverified","official":{"repos":["indiiigo/automatedcad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/targen-targeted-data-generation-with-large","slug":"targen-targeted-data-generation-with-large","title":"TarGEN: Targeted Data Generation with Large Language Models","date":"2023-10-27","arxiv_id":"2310.17876","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["kevinscaria/targen"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/background-summarization-of-event-timelines","slug":"background-summarization-of-event-timelines","title":"Background Summarization of Event Timelines","date":"2023-10-24","arxiv_id":"2310.16197","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-free-text-human-feedback","slug":"learning-from-free-text-human-feedback","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","date":"2023-10-24","arxiv_id":"2310.15758","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 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) · 1 unverified","official":{"repos":["ukplab/emnlp2023-learning-from-free-text-human-feedback"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-language-models-employ-the-socratic","slug":"can-language-models-employ-the-socratic","title":"Can Language Models Employ the Socratic Method? Experiments with Code Debugging","date":"2023-10-04","arxiv_id":"2310.03210","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-fine-tuning-of-llms-on-the-very","title":"Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly","date":"2023-10-04","arxiv_id":"2310.03150","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-ontology","slug":"exploring-large-language-models-for-ontology","title":"Exploring Large Language Models for Ontology Alignment","date":"2023-09-12","arxiv_id":"2309.07172","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-robustness-to-instructions-of","title":"Evaluating the Robustness to Instructions of Large Language Models","date":"2023-08-28","arxiv_id":"2308.14306","n_code_links":0,"syntology":null},{"paper":"/paper/zero-and-few-shot-prompting-with-llms-a","slug":"zero-and-few-shot-prompting-with-llms-a","title":"Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis","date":"2023-08-21","arxiv_id":"2308.10783","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-to-identify-social","slug":"large-language-models-to-identify-social","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","date":"2023-08-11","arxiv_id":"2308.06354","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aim-harvard/sdoh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructed-to-bias-instruction-tuned-language","slug":"instructed-to-bias-instruction-tuned-language","title":"Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias","date":"2023-08-01","arxiv_id":"2308.00225","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["itay1itzhak/instructedtobias"],"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":"tutorials-on-stance-detection-using-pre","title":"Tutorials on Stance Detection using Pre-trained Language Models: Fine-tuning BERT and Prompting Large Language Models","date":"2023-07-28","arxiv_id":"2307.15331","n_code_links":0,"syntology":null},{"paper":"/paper/watermarking-conditional-text-generation-for","slug":"watermarking-conditional-text-generation-for","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","date":"2023-07-25","arxiv_id":"2307.13808","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-zero-shot-and-few-shot-study-of-instruction","title":"A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks","date":"2023-07-22","arxiv_id":"2307.12114","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-generate-train-pgt-a-framework-for-few","title":"Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering","date":"2023-07-12","arxiv_id":"2307.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-efficacy-of-large-language","title":"Assessing the efficacy of large language models in generating accurate teacher responses","date":"2023-07-09","arxiv_id":"2307.04274","n_code_links":0,"syntology":null},{"paper":"/paper/text-alignment-is-an-efficient-unified-model","slug":"text-alignment-is-an-efficient-unified-model","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","date":"2023-07-06","arxiv_id":"2307.02729","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-bea-2023-shared-task-on-generating-ai","title":"The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-12","arxiv_id":"2306.06941","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-learning-user-simulators-for-task","slug":"in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","n_code_links":2,"syntology":null},{"paper":"/paper/fusecap-leveraging-large-language-models-to","slug":"fusecap-leveraging-large-language-models-to","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","date":"2023-05-28","arxiv_id":"2305.17718","n_code_links":1,"syntology":null},{"paper":"/paper/augmentation-adapted-retriever-improves","slug":"augmentation-adapted-retriever-improves","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","date":"2023-05-27","arxiv_id":"2305.17331","n_code_links":2,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["openmatch/augmentation-adapted-retriever"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"a-relentless-benchmark-for-modelling-graded","title":"A RelEntLess Benchmark for Modelling Graded Relations between Named Entities","date":"2023-05-24","arxiv_id":"2305.15002","n_code_links":0,"syntology":null},{"paper":"/paper/csts-conditional-semantic-textual-similarity","slug":"csts-conditional-semantic-textual-similarity","title":"C-STS: Conditional Semantic Textual Similarity","date":"2023-05-24","arxiv_id":"2305.15093","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["princeton-nlp/c-sts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/discriminator-guided-multi-step-reasoning","slug":"discriminator-guided-multi-step-reasoning","title":"GRACE: Discriminator-Guided Chain-of-Thought Reasoning","date":"2023-05-24","arxiv_id":"2305.14934","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-summarization-of-electronic-health","title":"Neural Summarization of Electronic Health Records","date":"2023-05-24","arxiv_id":"2305.15222","n_code_links":0,"syntology":null},{"paper":"/paper/trusting-your-evidence-hallucinate-less-with","slug":"trusting-your-evidence-hallucinate-less-with","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","date":"2023-05-24","arxiv_id":"2305.14739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/logicllm-exploring-self-supervised-logic","slug":"logicllm-exploring-self-supervised-logic","title":"Exploring Self-supervised Logic-enhanced Training for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13718","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sparkjiao/logicllm","sparkjiao/merit-v2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","n_code_links":2,"syntology":null},{"paper":"/paper/interpretable-word-sense-representations-via","slug":"interpretable-word-sense-representations-via","title":"Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis","date":"2023-05-19","arxiv_id":"2305.11993","n_code_links":1,"syntology":null},{"paper":"/paper/coedit-text-editing-by-task-specific","slug":"coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-zero-and-few-shot-techniques-for","title":"Exploring Zero and Few-shot Techniques for Intent Classification","date":"2023-05-11","arxiv_id":"2305.07157","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-relation-extraction-in-the-era-of","title":"Revisiting Relation Extraction in the era of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05003","n_code_links":0,"syntology":null},{"paper":"/paper/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":null,"slug":"empirical-analysis-of-the-strengths-and","title":"Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs","date":"2023-04-28","arxiv_id":"2304.14999","n_code_links":0,"syntology":null},{"paper":"/paper/tablet-learning-from-instructions-for-tabular","slug":"tablet-learning-from-instructions-for-tabular","title":"TABLET: Learning From Instructions For Tabular Data","date":"2023-04-25","arxiv_id":"2304.13188","n_code_links":1,"syntology":null},{"paper":null,"slug":"amr-parsing-with-instruction-fine-tuned-pre","title":"AMR Parsing with Instruction Fine-tuned Pre-trained Language Models","date":"2023-04-24","arxiv_id":"2304.12272","n_code_links":0,"syntology":null},{"paper":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","n_code_links":1,"syntology":null},{"paper":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","n_code_links":2,"syntology":null},{"paper":"/paper/spam-t5-benchmarking-large-language-models","slug":"spam-t5-benchmarking-large-language-models","title":"Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection","date":"2023-04-03","arxiv_id":"2304.01238","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":107,"with_a_code_link":57,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":107,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":6,"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":14,"papers_where_code_ran_first_page":"/method/flan-t5/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":2,"url":"/method/flan-t5/papers/2","json":"/method/flan-t5/papers/2.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/method/flan-t5/papers/ran/1","json":"/method/flan-t5/papers/ran/1.json","rows":14}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":22},{"task":"/task/question-answering","name":"Question Answering","papers":19},{"task":"/task/language-modeling","name":"Language Modeling","papers":18},{"task":"/task/large-language-model","name":"Large Language Model","papers":10},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":9},{"task":"/task/retrieval","name":"Retrieval","papers":8},{"task":"/task/sentence","name":"Sentence","papers":8},{"task":"/task/text-generation","name":"Text Generation","papers":7},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":6},{"task":"/task/benchmarking","name":"Benchmarking","papers":4},{"task":"/task/relation-extraction","name":"Relation Extraction","papers":4},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":4},{"task":"/task/attribute","name":"Attribute","papers":3},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":3},{"task":"/task/diagnostic","name":"Diagnostic","papers":3},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":3},{"task":"/task/mmlu","name":"MMLU","papers":3},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":3},{"task":"/task/reading-comprehension","name":"Reading Comprehension","papers":3}],"tasks_shown":20,"n_tasks":167,"usage_by_year":[{"year":"2022","papers":3},{"year":"2023","papers":47},{"year":"2024","papers":46},{"year":"2025","papers":11}],"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/flan-t5"},"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=Flan-T5","read_at":"2026-10-05T00:56:03+00:00","query":"Flan-T5","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":"Flan-T5","origin_arxiv_id":"2210.11416"},"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":"2210.11416","repositories":{"listed":5,"in_graph":10,"list_truncated":true,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2210.11416","citations":4394},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Flan-T5'. 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":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2210.11416","page":"/paper/scaling-instruction-finetuned-language-models","syntology_url":"https://syntology.ai/paper/2210.11416","in_graph_layer":true,"samples":17,"ran":8,"n_ran_checked":1,"n_instrument":7,"unverified":9,"phrase":"8 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; 7 where Syntology's instrument failed) · 9 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 10 in the graph, strongest link: mentioned on GitHub). This answer is about arXiv:2210.11416, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"42141fbfceaa2a15369b703ee0d5192c91e6305b46d0e1326de41f2a64ede8f3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}