{"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/discriminative-fine-tuning/papers/13","list_of":"/method/discriminative-fine-tuning","method":"Discriminative Fine-Tuning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":13,"pages_in_order":20,"rows_per_page":100,"rows":[1201,1300],"of":1990,"counts":{"archive_papers_tagged":1990,"with_a_code_link":794,"where_syntology_ran_a_sample":271,"not_listed_spam_title":0,"listed":1990,"listed_where_code_ran":271,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":223,"every_run_a_failure_of_syntologys_instrument":48,"listed_with_a_run_with_no_instrument_failure":223,"listed_every_run_a_failure_of_syntologys_instrument":48,"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"},"first_page":"/method/discriminative-fine-tuning","prev":"/method/discriminative-fine-tuning/papers/12","next":"/method/discriminative-fine-tuning/papers/14","papers":[{"paper":null,"slug":"holy-grail-2-0-from-natural-language-to","title":"Holy Grail 2.0: From Natural Language to Constraint Models","date":"2023-08-03","arxiv_id":"2308.01589","n_code_links":0,"syntology":null},{"paper":"/paper/seed-bench-benchmarking-multimodal-llms-with","slug":"seed-bench-benchmarking-multimodal-llms-with","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","date":"2023-07-30","arxiv_id":"2307.16125","n_code_links":3,"syntology":null},{"paper":"/paper/metric-based-in-context-learning-a-case-study","slug":"metric-based-in-context-learning-a-case-study","title":"Metric-Based In-context Learning: A Case Study in Text Simplification","date":"2023-07-27","arxiv_id":"2307.14632","n_code_links":1,"syntology":null},{"paper":"/paper/new-interaction-paradigm-for-complex-eda","slug":"new-interaction-paradigm-for-complex-eda","title":"New Interaction Paradigm for Complex EDA Software Leveraging GPT","date":"2023-07-27","arxiv_id":"2307.14740","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":["smarton-empower/smarton-ai"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"textmania-enriching-visual-feature-by-text","title":"TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation","date":"2023-07-27","arxiv_id":"2307.14611","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-a-computational-model-of-emotion","title":"Is GPT a Computational Model of Emotion? Detailed Analysis","date":"2023-07-25","arxiv_id":"2307.13779","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-for-software-security-exploring-the","slug":"chatgpt-for-software-security-exploring-the","title":"How Does Naming Affect LLMs on Code Analysis Tasks?","date":"2023-07-24","arxiv_id":"2307.12488","n_code_links":0,"syntology":null},{"paper":"/paper/testing-hateful-speeches-against-policies","slug":"testing-hateful-speeches-against-policies","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","date":"2023-07-23","arxiv_id":"2307.12418","n_code_links":1,"syntology":null},{"paper":null,"slug":"aigc-empowering-telecom-sector-white-paper","title":"AIGC Empowering Telecom Sector White Paper_chinese","date":"2023-07-21","arxiv_id":"2307.11449","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-federated-learning","slug":"a-systematic-evaluation-of-federated-learning","title":"An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing","date":"2023-07-20","arxiv_id":"2307.11254","n_code_links":2,"syntology":null},{"paper":"/paper/ivygpt-interactive-chinese-pathway-language","slug":"ivygpt-interactive-chinese-pathway-language","title":"IvyGPT: InteractiVe Chinese pathwaY language model in medical domain","date":"2023-07-20","arxiv_id":"2307.10512","n_code_links":1,"syntology":null},{"paper":"/paper/of-models-and-tin-men-a-behavioural-economics","slug":"of-models-and-tin-men-a-behavioural-economics","title":"Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models","date":"2023-07-20","arxiv_id":"2307.11137","n_code_links":2,"syntology":null},{"paper":null,"slug":"generating-mathematical-derivations-with","title":"Controlling Equational Reasoning in Large Language Models with Prompt Interventions","date":"2023-07-19","arxiv_id":"2307.09998","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveiling-gender-bias-in-terms-of-profession","title":"Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications","date":"2023-07-18","arxiv_id":"2307.09162","n_code_links":0,"syntology":null},{"paper":"/paper/a-mixed-policy-to-improve-performance-of","slug":"a-mixed-policy-to-improve-performance-of","title":"A mixed policy to improve performance of language models on math problems","date":"2023-07-17","arxiv_id":"2307.08767","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-on-the-performance-of-generative-pre","title":"A Study on the Performance of Generative Pre-trained Transformer (GPT) in Simulating Depressed Individuals on the Standardized Depressive Symptom Scale","date":"2023-07-17","arxiv_id":"2307.08576","n_code_links":0,"syntology":null},{"paper":"/paper/sentimentgpt-exploiting-gpt-for-advanced","slug":"sentimentgpt-exploiting-gpt-for-advanced","title":"SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning","date":"2023-07-16","arxiv_id":"2307.10234","n_code_links":1,"syntology":null},{"paper":"/paper/fairness-of-chatgpt-and-the-role-of","slug":"fairness-of-chatgpt-and-the-role-of","title":"Fairness of ChatGPT and the Role Of Explainable-Guided Prompts","date":"2023-07-14","arxiv_id":"2307.11761","n_code_links":1,"syntology":null},{"paper":null,"slug":"morphpiece-moving-away-from-statistical","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","date":"2023-07-14","arxiv_id":"2307.07262","n_code_links":0,"syntology":null},{"paper":"/paper/ashaar-automatic-analysis-and-generation-of","slug":"ashaar-automatic-analysis-and-generation-of","title":"Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches","date":"2023-07-12","arxiv_id":"2307.06218","n_code_links":1,"syntology":null},{"paper":null,"slug":"dnagpt-a-generalized-pretrained-tool-for","title":"DNAGPT: A Generalized Pre-trained Tool for Versatile DNA Sequence Analysis Tasks","date":"2023-07-11","arxiv_id":"2307.05628","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models","title":"Large Language Models","date":"2023-07-11","arxiv_id":"2307.05782","n_code_links":0,"syntology":null},{"paper":null,"slug":"named-entity-recognition-using-gpt-for","title":"Named entity recognition using GPT for identifying comparable companies","date":"2023-07-11","arxiv_id":"2307.07420","n_code_links":0,"syntology":null},{"paper":"/paper/amadeusgpt-a-natural-language-interface-for-1","slug":"amadeusgpt-a-natural-language-interface-for-1","title":"AmadeusGPT: a natural language interface for interactive animal behavioral analysis","date":"2023-07-10","arxiv_id":"2307.04858","n_code_links":1,"syntology":null},{"paper":null,"slug":"simplemtod-a-simple-language-model-for","title":"SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation","date":"2023-07-10","arxiv_id":"2307.04907","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":null,"slug":"goal-conditioned-predictive-coding-as-an","title":"Goal-Conditioned Predictive Coding for Offline Reinforcement Learning","date":"2023-07-07","arxiv_id":"2307.03406","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-empowered-autonomous","title":"Large Language Models Empowered Autonomous Edge AI for Connected Intelligence","date":"2023-07-06","arxiv_id":"2307.02779","n_code_links":0,"syntology":null},{"paper":"/paper/came-confidence-guided-adaptive-memory","slug":"came-confidence-guided-adaptive-memory","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","date":"2023-07-05","arxiv_id":"2307.02047","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["yangluo7/came","huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-effectiveness-of-large","title":"Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations","date":"2023-07-05","arxiv_id":"2307.03678","n_code_links":0,"syntology":null},{"paper":null,"slug":"tensorgpt-efficient-compression-of-the","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","date":"2023-07-02","arxiv_id":"2307.00526","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-for-automating","title":"Large Language Models (GPT) for automating feedback on programming assignments","date":"2023-06-30","arxiv_id":"2307.00150","n_code_links":0,"syntology":null},{"paper":null,"slug":"spae-semantic-pyramid-autoencoder-for","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","date":"2023-06-30","arxiv_id":"2306.17842","n_code_links":0,"syntology":null},{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-negation-detection-assessment-of-gpts","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","date":"2023-06-29","arxiv_id":"2306.16638","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparseoptimizer-sparsify-language-models","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","date":"2023-06-27","arxiv_id":"2306.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-design-by-integrating-a-large-pre","title":"Interactive Design by Integrating a Large Pre-Trained Language Model and Building Information Modeling","date":"2023-06-25","arxiv_id":"2306.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-pre-training-truly-better-than-meta","title":"Is Pre-training Truly Better Than Meta-Learning?","date":"2023-06-24","arxiv_id":"2306.13841","n_code_links":0,"syntology":null},{"paper":"/paper/voicebox-text-guided-multilingual-universal","slug":"voicebox-text-guided-multilingual-universal","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","date":"2023-06-23","arxiv_id":"2306.15687","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"black-box-prediction-of-flaky-test-fix","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","date":"2023-06-21","arxiv_id":"2307.00012","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-pre-trained-language-models-on","title":"Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI","date":"2023-06-21","arxiv_id":"2306.12205","n_code_links":0,"syntology":null},{"paper":null,"slug":"decodingtrust-a-comprehensive-assessment-of","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","date":"2023-06-20","arxiv_id":"2306.11698","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-gpt-a-data-pre-processing-and-1","slug":"event-stream-gpt-a-data-pre-processing-and-1","title":"Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events","date":"2023-06-20","arxiv_id":"2306.11547","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mmcdermott/eventstreamgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/inrank-incremental-low-rank-learning","slug":"inrank-incremental-low-rank-learning","title":"InRank: Incremental Low-Rank Learning","date":"2023-06-20","arxiv_id":"2306.11250","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-better-than-your-llm","slug":"learning-to-generate-better-than-your-llm","title":"Learning to Generate Better Than Your LLM","date":"2023-06-20","arxiv_id":"2306.11816","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-sequential-recommendation-with","title":"Generative Sequential Recommendation with GPTRec","date":"2023-06-19","arxiv_id":"2306.11114","n_code_links":0,"syntology":null},{"paper":null,"slug":"synergpt-in-context-learning-for-personalized","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","date":"2023-06-19","arxiv_id":"2307.11694","n_code_links":0,"syntology":null},{"paper":"/paper/gpt4-is-slightly-helpful-for-peer-review","slug":"gpt4-is-slightly-helpful-for-peer-review","title":"GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study","date":"2023-06-16","arxiv_id":"2307.05492","n_code_links":2,"syntology":null},{"paper":"/paper/chessgpt-bridging-policy-learning-and-1","slug":"chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","arxiv_id":"2306.09200","n_code_links":1,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["waterhorse1/chessgpt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/explore-establish-exploit-red-teaming","slug":"explore-establish-exploit-red-teaming","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","date":"2023-06-15","arxiv_id":"2306.09442","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["algorithmic-alignment-lab/commonclaim","thestephencasper/common_claim","thestephencasper/explore_establish_exploit_llms"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"the-pop-song-generator-designing-an-online","title":"The pop song generator: designing an online course to teach collaborative, creative AI","date":"2023-06-15","arxiv_id":"2306.10069","n_code_links":0,"syntology":null},{"paper":null,"slug":"thrilled-by-your-progress-large-language","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","date":"2023-06-15","arxiv_id":"2306.10073","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-agi-in-computer-vision-lessons","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","date":"2023-06-14","arxiv_id":"2306.08641","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-n-gram-approximation-of-pre-trained","title":"On the N-gram Approximation of Pre-trained Language Models","date":"2023-06-12","arxiv_id":"2306.06892","n_code_links":0,"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":null,"slug":"gpt-calls-enhancing-call-segmentation-and","title":"GPT-Calls: Enhancing Call Segmentation and Tagging by Generating Synthetic Conversations via Large Language Models","date":"2023-06-09","arxiv_id":"2306.07941","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-can-learn-exceptions-to","slug":"language-models-can-learn-exceptions-to","title":"Language Models Can Learn Exceptions to Syntactic Rules","date":"2023-06-09","arxiv_id":"2306.05969","n_code_links":1,"syntology":null},{"paper":"/paper/prodigy-an-expeditiously-adaptive-parameter","slug":"prodigy-an-expeditiously-adaptive-parameter","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","date":"2023-06-09","arxiv_id":"2306.06101","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-telecom-language-through-large","title":"Understanding Telecom Language Through Large Language Models","date":"2023-06-09","arxiv_id":"2306.07933","n_code_links":0,"syntology":null},{"paper":"/paper/check-me-if-you-can-detecting-chatgpt","slug":"check-me-if-you-can-detecting-chatgpt","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","date":"2023-06-07","arxiv_id":"2306.05524","n_code_links":2,"syntology":null},{"paper":null,"slug":"gpt-self-supervision-for-a-better-data","title":"GPT Self-Supervision for a Better Data Annotator","date":"2023-06-07","arxiv_id":"2306.04349","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-analysis-of-parameter-efficient","slug":"an-empirical-analysis-of-parameter-efficient","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.04067","n_code_links":1,"syntology":null},{"paper":null,"slug":"iterative-translation-refinement-with-large","title":"Iterative Translation Refinement with Large Language Models","date":"2023-06-06","arxiv_id":"2306.03856","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-acquisition-do-children-and-language","title":"Language acquisition: do children and language models follow similar learning stages?","date":"2023-06-06","arxiv_id":"2306.03586","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-gpt-model-pre-training-using-tensor","title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation","date":"2023-06-05","arxiv_id":"2306.02697","n_code_links":0,"syntology":null},{"paper":null,"slug":"stack-over-flowing-with-results-the-case-for","title":"Skill over Scale: The Case for Medium, Domain-Specific Models for SE","date":"2023-06-05","arxiv_id":"2306.03268","n_code_links":0,"syntology":null},{"paper":"/paper/can-contextual-biasing-remain-effective-with","slug":"can-contextual-biasing-remain-effective-with","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","date":"2023-06-02","arxiv_id":"2306.01942","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-glossary-of-clinical-terminology-a","title":"Automatic Glossary of Clinical Terminology: a Large-Scale Dictionary of Biomedical Definitions Generated from Ontological Knowledge","date":"2023-06-01","arxiv_id":"2306.00665","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-programming-etextbooks-with-chatgpt","title":"Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions","date":"2023-06-01","arxiv_id":"2306.00551","n_code_links":0,"syntology":null},{"paper":null,"slug":"topex-topic-based-explanations-for-model","title":"TopEx: Topic-based Explanations for Model Comparison","date":"2023-06-01","arxiv_id":"2306.00976","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gpt-s-programming-capability","title":"Evaluating GPT's Programming Capability through CodeWars' Katas","date":"2023-05-31","arxiv_id":"2306.01784","n_code_links":0,"syntology":null},{"paper":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-models-in-construction-industry","title":"GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation","date":"2023-05-30","arxiv_id":"2305.18997","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-seeds-beyond-weeds-green-teaming","title":"Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses","date":"2023-05-30","arxiv_id":"2306.03097","n_code_links":0,"syntology":null},{"paper":null,"slug":"processgpt-transforming-business-process","title":"ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence","date":"2023-05-29","arxiv_id":"2306.01771","n_code_links":0,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-language-models-handle-word","title":"Transformer Language Models Handle Word Frequency in Prediction Head","date":"2023-05-29","arxiv_id":"2305.18294","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-language-barriers-with-a-leap","title":"Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs","date":"2023-05-28","arxiv_id":"2305.17740","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-for-power-outage-detection","title":"Transfer Learning for Power Outage Detection Task with Limited Training Data","date":"2023-05-28","arxiv_id":"2305.17817","n_code_links":0,"syntology":null},{"paper":"/paper/model-dementia-generated-data-makes-models","slug":"model-dementia-generated-data-makes-models","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","date":"2023-05-27","arxiv_id":"2305.17493","n_code_links":1,"syntology":null},{"paper":"/paper/backpack-language-models","slug":"backpack-language-models","title":"Backpack Language Models","date":"2023-05-26","arxiv_id":"2305.16765","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/chain-of-thought-hub-a-continuous-effort-to","slug":"chain-of-thought-hub-a-continuous-effort-to","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","date":"2023-05-26","arxiv_id":"2305.17306","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["franxyao/chain-of-thought-hub"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-and-leveraging-verifiers-to-improve","title":"Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models","date":"2023-05-26","arxiv_id":"2305.17077","n_code_links":0,"syntology":null},{"paper":"/paper/llms-and-the-abstraction-and-reasoning-corpus","slug":"llms-and-the-abstraction-and-reasoning-corpus","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","date":"2023-05-26","arxiv_id":"2305.18354","n_code_links":1,"syntology":null},{"paper":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gengzezhou/navgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"a-survey-on-chatgpt-ai-generated-contents","title":"A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions","date":"2023-05-25","arxiv_id":"2305.18339","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-wacky-vs-definitely-wacky-a-study-of","title":"Not wacky vs. definitely wacky: A study of scalar adverbs in pretrained language models","date":"2023-05-25","arxiv_id":"2305.16426","n_code_links":0,"syntology":null},{"paper":null,"slug":"don-t-take-this-out-of-context-on-the-need","title":"Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting","date":"2023-05-24","arxiv_id":"2305.14755","n_code_links":0,"syntology":null},{"paper":null,"slug":"don-t-trust-gpt-when-your-question-is-not-in","title":"Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs","date":"2023-05-24","arxiv_id":"2305.16339","n_code_links":0,"syntology":null},{"paper":"/paper/editing-commonsense-knowledge-in-gpt","slug":"editing-commonsense-knowledge-in-gpt","title":"Editing Common Sense in Transformers","date":"2023-05-24","arxiv_id":"2305.14956","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["anshitag/memit_csk"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/have-llms-advanced-enough-a-challenging","slug":"have-llms-advanced-enough-a-challenging","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","date":"2023-05-24","arxiv_id":"2305.15074","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 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) · 0 unverified","official":{"repos":["hgaurav2k/jeebench"],"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":"/paper/inference-time-policy-adapters-ipa-tailoring","slug":"inference-time-policy-adapters-ipa-tailoring","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","date":"2023-05-24","arxiv_id":"2305.15065","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":5,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gximinglu/ipa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tricking-llms-into-disobedience-understanding","slug":"tricking-llms-into-disobedience-understanding","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","date":"2023-05-24","arxiv_id":"2305.14965","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":["AetherPrior/TrickLLM"],"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/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":null,"slug":"a-trip-towards-fairness-bias-and-de-biasing","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","date":"2023-05-23","arxiv_id":"2305.13862","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-principles-for-in-context","title":"Active Learning Principles for In-Context Learning with Large Language Models","date":"2023-05-23","arxiv_id":"2305.14264","n_code_links":0,"syntology":null},{"paper":null,"slug":"deduction-under-perturbed-evidence-probing","title":"Deduction under Perturbed Evidence: Probing Student Simulation Capabilities of Large Language Models","date":"2023-05-23","arxiv_id":"2305.14507","n_code_links":0,"syntology":null}],"record_sha256":"86b814f78e0273132af8cd340ed26158be1d4c3b9fa68578fff4416a9478fd6b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}