{"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/papers/12","list_of":"/method/gpt-3","method":"GPT-3","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":12,"pages_in_order":20,"rows_per_page":100,"rows":[1101,1200],"of":1906,"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":259,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":259,"listed_every_run_a_failure_of_syntologys_instrument":60,"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/gpt-3","prev":"/method/gpt-3/papers/11","next":"/method/gpt-3/papers/13","papers":[{"paper":null,"slug":"strategic-behavior-of-large-language-models","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","date":"2023-09-12","arxiv_id":"2309.05898","n_code_links":0,"syntology":null},{"paper":"/paper/the-moral-machine-experiment-on-large","slug":"the-moral-machine-experiment-on-large","title":"The Moral Machine Experiment on Large Language Models","date":"2023-09-12","arxiv_id":"2309.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-the-potential-of-large-language","title":"Unveiling the potential of large language models in generating semantic and cross-language clones","date":"2023-09-12","arxiv_id":"2309.06424","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-analysis-gpts-across-time-in-legal","title":"Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task","date":"2023-09-11","arxiv_id":"2309.05501","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-learning-with-minimum-instruction","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","date":"2023-09-11","arxiv_id":"2309.05475","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-learning-principles-with-a","title":"Implementing Learning Principles with a Personal AI Tutor: A Case Study","date":"2023-09-10","arxiv_id":"2309.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-identify-distinguish-and","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","date":"2023-09-08","arxiv_id":"2309.04635","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-tuning-for-vision","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","date":"2023-09-08","arxiv_id":"2309.04158","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-as-a-recommender-system-a","slug":"evaluating-chatgpt-as-a-recommender-system-a","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","date":"2023-09-07","arxiv_id":"2309.03613","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","n_code_links":2,"syntology":null},{"paper":null,"slug":"flm-101b-an-open-llm-and-how-to-train-it-with","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","date":"2023-09-07","arxiv_id":"2309.03852","n_code_links":0,"syntology":null},{"paper":"/paper/hae-rae-bench-evaluation-of-korean-knowledge","slug":"hae-rae-bench-evaluation-of-korean-knowledge","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","date":"2023-09-06","arxiv_id":"2309.02706","n_code_links":1,"syntology":null},{"paper":"/paper/prompting-or-fine-tuning-a-comparative-study","slug":"prompting-or-fine-tuning-a-comparative-study","title":"Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction","date":"2023-09-04","arxiv_id":"2309.01715","n_code_links":1,"syntology":null},{"paper":"/paper/saturn-an-optimized-data-system-for-large","slug":"saturn-an-optimized-data-system-for-large","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","date":"2023-09-03","arxiv_id":"2309.01226","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-semantic-monitoring","title":"Large Language Models for Semantic Monitoring of Corporate Disclosures: A Case Study on Korea's Top 50 KOSPI Companies","date":"2023-09-01","arxiv_id":"2309.00208","n_code_links":0,"syntology":null},{"paper":"/paper/publicly-shareable-clinical-large-language","slug":"publicly-shareable-clinical-large-language","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","date":"2023-09-01","arxiv_id":"2309.00237","n_code_links":1,"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":["starmpcc/asclepius"],"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/taken-out-of-context-on-measuring-situational","slug":"taken-out-of-context-on-measuring-situational","title":"Taken out of context: On measuring situational awareness in LLMs","date":"2023-09-01","arxiv_id":"2309.00667","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["asacooperstickland/situational-awareness-evals"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","n_code_links":1,"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":["gersteinlab/biocoder"],"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":"gpt-has-become-financially-literate-insights","title":"GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice","date":"2023-08-31","arxiv_id":"2309.00649","n_code_links":0,"syntology":null},{"paper":null,"slug":"ladder-of-thought-using-knowledge-as-steps-to","title":"Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection","date":"2023-08-31","arxiv_id":"2308.16763","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarathi-efficient-llm-inference-by","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","date":"2023-08-31","arxiv_id":"2308.16369","n_code_links":0,"syntology":null},{"paper":null,"slug":"jais-and-jais-chat-arabic-centric-foundation","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","date":"2023-08-30","arxiv_id":"2308.16149","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-data-preprocessors","title":"Large Language Models as Data Preprocessors","date":"2023-08-30","arxiv_id":"2308.16361","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-uncertainty-in-answers-from-any","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","date":"2023-08-30","arxiv_id":"2308.16175","n_code_links":0,"syntology":null},{"paper":"/paper/response-emergent-analogical-reasoning-in","slug":"response-emergent-analogical-reasoning-in","title":"Response: Emergent analogical reasoning in large language models","date":"2023-08-30","arxiv_id":"2308.16118","n_code_links":1,"syntology":null},{"paper":null,"slug":"furchat-an-embodied-conversational-agent","title":"FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions","date":"2023-08-29","arxiv_id":"2308.15214","n_code_links":0,"syntology":null},{"paper":"/paper/multi-party-goal-tracking-with-llms-comparing","slug":"multi-party-goal-tracking-with-llms-comparing","title":"Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering","date":"2023-08-29","arxiv_id":"2308.15231","n_code_links":1,"syntology":null},{"paper":null,"slug":"breaking-the-bank-with-chatgpt-few-shot-text","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","date":"2023-08-28","arxiv_id":"2308.14634","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-effects-in-large-language-models","slug":"cognitive-effects-in-large-language-models","title":"Cognitive Effects in Large Language Models","date":"2023-08-28","arxiv_id":"2308.14337","n_code_links":1,"syntology":null},{"paper":"/paper/distilled-gpt-for-source-code-summarization","slug":"distilled-gpt-for-source-code-summarization","title":"Distilled GPT for Source Code Summarization","date":"2023-08-28","arxiv_id":"2308.14731","n_code_links":1,"syntology":null},{"paper":"/paper/a-wide-evaluation-of-chatgpt-on-affective","slug":"a-wide-evaluation-of-chatgpt-on-affective","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","date":"2023-08-26","arxiv_id":"2308.13911","n_code_links":1,"syntology":null},{"paper":"/paper/cultural-alignment-in-large-language-models","slug":"cultural-alignment-in-large-language-models","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","date":"2023-08-25","arxiv_id":"2309.12342","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-on-graphs","slug":"evaluating-large-language-models-on-graphs","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","date":"2023-08-22","arxiv_id":"2308.11224","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 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) · 2 unverified","official":{"repos":["ayame1006/llmtograph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-effectiveness-of-gpt-models-in","title":"Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test","date":"2023-08-22","arxiv_id":"2308.11827","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-as-a-user-simulator","slug":"large-language-model-as-a-user-simulator","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","date":"2023-08-21","arxiv_id":"2308.11534","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"0 ran · 2 unverified","official":null}},{"paper":"/paper/large-language-models-on-wikipedia-style","slug":"large-language-models-on-wikipedia-style","title":"Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts","date":"2023-08-21","arxiv_id":"2308.10410","n_code_links":1,"syntology":null},{"paper":"/paper/data-to-text-generation-for-severely-under","slug":"data-to-text-generation-for-severely-under","title":"Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate","date":"2023-08-19","arxiv_id":"2308.09957","n_code_links":1,"syntology":null},{"paper":"/paper/how-susceptible-are-llms-to-logical-fallacies","slug":"how-susceptible-are-llms-to-logical-fallacies","title":"How susceptible are LLMs to Logical Fallacies?","date":"2023-08-18","arxiv_id":"2308.09853","n_code_links":1,"syntology":null},{"paper":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":16,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluation-of-really-good-grammatical-error","slug":"evaluation-of-really-good-grammatical-error","title":"Evaluation of really good grammatical error correction","date":"2023-08-17","arxiv_id":"2308.08982","n_code_links":1,"syntology":null},{"paper":null,"slug":"mascqa-a-question-answering-dataset-for","title":"MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models","date":"2023-08-17","arxiv_id":"2308.09115","n_code_links":0,"syntology":null},{"paper":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"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) · 2 unverified","official":{"repos":["wyl-willing/MindMap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"self-deception-reverse-penetrating-the","title":"Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models","date":"2023-08-16","arxiv_id":"2308.11521","n_code_links":0,"syntology":null},{"paper":null,"slug":"backward-reasoning-in-large-language-models","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","date":"2023-08-15","arxiv_id":"2308.07758","n_code_links":0,"syntology":null},{"paper":null,"slug":"calypso-llms-as-dungeon-masters-assistants","title":"CALYPSO: LLMs as Dungeon Masters' Assistants","date":"2023-08-15","arxiv_id":"2308.07540","n_code_links":0,"syntology":null},{"paper":"/paper/from-commit-message-generation-to-history","slug":"from-commit-message-generation-to-history","title":"From Commit Message Generation to History-Aware Commit Message Completion","date":"2023-08-15","arxiv_id":"2308.07655","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-student-errors-in-experimentation","title":"Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters","date":"2023-08-11","arxiv_id":"2308.06088","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-phenotype-recognition-in-clinical","slug":"enhancing-phenotype-recognition-in-clinical","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","date":"2023-08-11","arxiv_id":"2308.06294","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-in-cryptocurrency","title":"Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?","date":"2023-08-11","arxiv_id":"2308.06032","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-low-rank-adaptation-of-segment","slug":"adaptive-low-rank-adaptation-of-segment","title":"Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection","date":"2023-08-10","arxiv_id":"2308.05426","n_code_links":1,"syntology":null},{"paper":"/paper/metacognitive-prompting-improves","slug":"metacognitive-prompting-improves","title":"Metacognitive Prompting Improves Understanding in Large Language Models","date":"2023-08-10","arxiv_id":"2308.05342","n_code_links":1,"syntology":null},{"paper":"/paper/rtllm-an-open-source-benchmark-for-design-rtl","slug":"rtllm-an-open-source-benchmark-for-design-rtl","title":"RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model","date":"2023-08-10","arxiv_id":"2308.05345","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkust-zhiyao/rtllm"],"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":["official"]}}},{"paper":"/paper/you-only-prompt-once-on-the-capabilities-of","slug":"you-only-prompt-once-on-the-capabilities-of","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","date":"2023-08-10","arxiv_id":"2308.05596","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 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) · 0 unverified","official":{"repos":["xinleihe/toxic-prompt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llama-e-empowering-e-commerce-authoring-with","title":"LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following","date":"2023-08-09","arxiv_id":"2308.04913","n_code_links":0,"syntology":null},{"paper":"/paper/3d-vista-pre-trained-transformer-for-3d","slug":"3d-vista-pre-trained-transformer-for-3d","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","date":"2023-08-08","arxiv_id":"2308.04352","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"comparing-color-similarity-structures-between","title":"Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models","date":"2023-08-08","arxiv_id":"2308.04381","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-chatgpt-s-empathic-abilities","slug":"exploring-chatgpt-s-empathic-abilities","title":"Exploring ChatGPT's Empathic Abilities","date":"2023-08-07","arxiv_id":"2308.03527","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-detailed-oncologic-history-and","slug":"extracting-detailed-oncologic-history-and","title":"CORAL: Expert-Curated medical Oncology Reports to Advance Language Model Inference","date":"2023-08-07","arxiv_id":"2308.03853","n_code_links":1,"syntology":null},{"paper":"/paper/kitlm-domain-specific-knowledge-integration","slug":"kitlm-domain-specific-knowledge-integration","title":"KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering","date":"2023-08-07","arxiv_id":"2308.03638","n_code_links":1,"syntology":null},{"paper":null,"slug":"topological-interpretations-of-gpt-3","title":"Topological Interpretations of GPT-3","date":"2023-08-07","arxiv_id":"2308.03565","n_code_links":0,"syntology":null},{"paper":null,"slug":"kurosawa-a-script-writer-s-assistant","title":"\"Kurosawa\": A Script Writer's Assistant","date":"2023-08-06","arxiv_id":"2308.03122","n_code_links":0,"syntology":null},{"paper":null,"slug":"tarjamat-evaluation-of-bard-and-chatgpt-on","title":"TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties","date":"2023-08-06","arxiv_id":"2308.03051","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-for-gtfs-from-words-to-information","slug":"chatgpt-for-gtfs-from-words-to-information","title":"ChatGPT for GTFS: Benchmarking LLMs on GTFS Understanding and Retrieval","date":"2023-08-04","arxiv_id":"2308.02618","n_code_links":1,"syntology":null},{"paper":"/paper/baby-s-cothought-leveraging-large-language","slug":"baby-s-cothought-leveraging-large-language","title":"Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models","date":"2023-08-03","arxiv_id":"2308.01684","n_code_links":1,"syntology":null},{"paper":"/paper/classeval-a-manually-crafted-benchmark-for","slug":"classeval-a-manually-crafted-benchmark-for","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","date":"2023-08-03","arxiv_id":"2308.01861","n_code_links":2,"syntology":null},{"paper":null,"slug":"leveraging-few-shot-data-augmentation-and","title":"Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation","date":"2023-08-02","arxiv_id":"2308.01080","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-paradigm-shifts-in-artificial","title":"The Paradigm Shifts in Artificial Intelligence","date":"2023-08-02","arxiv_id":"2308.02558","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatmof-an-autonomous-ai-system-for","title":"ChatMOF: An Autonomous AI System for Predicting and Generating Metal-Organic Frameworks","date":"2023-08-01","arxiv_id":"2308.01423","n_code_links":0,"syntology":null},{"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":"/paper/towards-effective-ancient-chinese-translation","slug":"towards-effective-ancient-chinese-translation","title":"Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation","date":"2023-08-01","arxiv_id":"2308.00240","n_code_links":1,"syntology":null},{"paper":"/paper/does-fine-tuning-gpt-3-with-the-openai-api","slug":"does-fine-tuning-gpt-3-with-the-openai-api","title":"Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?","date":"2023-07-31","arxiv_id":"2307.16382","n_code_links":1,"syntology":null},{"paper":"/paper/hagrid-a-human-llm-collaborative-dataset-for","slug":"hagrid-a-human-llm-collaborative-dataset-for","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","date":"2023-07-31","arxiv_id":"2307.16883","n_code_links":1,"syntology":null},{"paper":"/paper/no-that-s-not-what-i-meant-handling-third","slug":"no-that-s-not-what-i-meant-handling-third","title":"No that's not what I meant: Handling Third Position Repair in Conversational Question Answering","date":"2023-07-31","arxiv_id":"2307.16689","n_code_links":1,"syntology":null},{"paper":null,"slug":"ontology-engineering-with-large-language","title":"Ontology engineering with Large Language Models","date":"2023-07-31","arxiv_id":"2307.16699","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-chatgpt-and-gpt-4-for-visual","title":"Evaluating ChatGPT and GPT-4 for Visual Programming","date":"2023-07-30","arxiv_id":"2308.02522","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-critical-review-of-large-language-models","title":"A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI","date":"2023-07-28","arxiv_id":"2307.15425","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-reality-the-pivotal-role-of-generative","title":"Beyond Reality: The Pivotal Role of Generative AI in the Metaverse","date":"2023-07-28","arxiv_id":"2308.06272","n_code_links":0,"syntology":null},{"paper":"/paper/med-halt-medical-domain-hallucination-test","slug":"med-halt-medical-domain-hallucination-test","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","date":"2023-07-28","arxiv_id":"2307.15343","n_code_links":1,"syntology":null},{"paper":null,"slug":"verigen-a-large-language-model-for-verilog","title":"VeriGen: A Large Language Model for Verilog Code Generation","date":"2023-07-28","arxiv_id":"2308.00708","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-generative-models-for-graph-to","slug":"evaluating-generative-models-for-graph-to","title":"Evaluating Generative Models for Graph-to-Text Generation","date":"2023-07-27","arxiv_id":"2307.14712","n_code_links":1,"syntology":null},{"paper":null,"slug":"clinidigest-a-case-study-in-large-language","title":"CliniDigest: A Case Study in Large Language Model Based Large-Scale Summarization of Clinical Trial Descriptions","date":"2023-07-26","arxiv_id":"2307.14522","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-user-language-affects-conflict-fatality","title":"How User Language Affects Conflict Fatality Estimates in ChatGPT","date":"2023-07-26","arxiv_id":"2308.00072","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-for-mental","slug":"leveraging-large-language-models-for-mental","title":"Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data","date":"2023-07-26","arxiv_id":"2307.14385","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-3-models-are-few-shot-financial-reasoners","title":"GPT-3 Models are Few-Shot Financial Reasoners","date":"2023-07-25","arxiv_id":"2307.13617","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-code-coverage-without-execution","slug":"predicting-code-coverage-without-execution","title":"Predicting Code Coverage without Execution","date":"2023-07-25","arxiv_id":"2307.13383","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-the-existence-of-secret","title":"Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models","date":"2023-07-24","arxiv_id":"2307.12507","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-potential-of-llms-for-coding-with-low","title":"The potential of LLMs for coding with low-resource and domain-specific programming languages","date":"2023-07-24","arxiv_id":"2307.13018","n_code_links":0,"syntology":null},{"paper":"/paper/validation-of-a-zero-shot-learning-natural","slug":"validation-of-a-zero-shot-learning-natural","title":"Validation of a Zero-Shot Learning Natural Language Processing Tool for Data Abstraction from Unstructured Healthcare Data","date":"2023-07-23","arxiv_id":"2308.00107","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-4-can-t-reason","title":"GPT-4 Can't Reason","date":"2023-07-21","arxiv_id":"2308.03762","n_code_links":0,"syntology":null},{"paper":"/paper/generative-language-models-on-nucleotide","slug":"generative-language-models-on-nucleotide","title":"Generative Language Models on Nucleotide Sequences of Human Genes","date":"2023-07-20","arxiv_id":"2307.10634","n_code_links":1,"syntology":null},{"paper":"/paper/llm-cognitive-judgements-differ-from-human","slug":"llm-cognitive-judgements-differ-from-human","title":"LLM Cognitive Judgements Differ From Human","date":"2023-07-20","arxiv_id":"2307.11787","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["sotlampr/llm-cognitive-judgements"],"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/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":"/paper/how-is-chatgpt-s-behavior-changing-over-time","slug":"how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lchen001/llmdrift"],"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":["listed","official"]}}},{"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":null,"slug":"chatgpt-is-good-but-bing-chat-is-better-for","title":"ChatGPT is Good but Bing Chat is Better for Vietnamese Students","date":"2023-07-17","arxiv_id":"2307.08272","n_code_links":0,"syntology":null},{"paper":"/paper/gear-augmenting-language-models-with","slug":"gear-augmenting-language-models-with","title":"GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution","date":"2023-07-17","arxiv_id":"2307.08775","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["yining610/gear"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"in-ide-generation-based-information-support","title":"Using an LLM to Help With Code Understanding","date":"2023-07-17","arxiv_id":"2307.08177","n_code_links":0,"syntology":null},{"paper":"/paper/legal-syllogism-prompting-teaching-large","slug":"legal-syllogism-prompting-teaching-large","title":"Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction","date":"2023-07-17","arxiv_id":"2307.08321","n_code_links":1,"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}],"record_sha256":"097cc2febb1de8f15a0ceb5d265325ccce43d9b38cf83d70d92077aab1421346","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}