{"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/cosine-annealing/papers/26","list_of":"/method/cosine-annealing","method":"Cosine Annealing","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":26,"pages_in_order":40,"rows_per_page":100,"rows":[2501,2600],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/25","next":"/method/cosine-annealing/papers/27","papers":[{"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":"/paper/knowledge-base-question-answering-for-space","slug":"knowledge-base-question-answering-for-space","title":"Knowledge Base Question Answering for Space Debris Queries","date":"2023-05-31","arxiv_id":"2305.19734","n_code_links":1,"syntology":null},{"paper":null,"slug":"does-conceptual-representation-require","title":"Does Conceptual Representation Require Embodiment? Insights From Large Language Models","date":"2023-05-30","arxiv_id":"2305.19103","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-select-open-ended-visual","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","date":"2023-05-30","arxiv_id":"2305.18842","n_code_links":0,"syntology":null},{"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":"/paper/check-covid-fact-checking-covid-19-news","slug":"check-covid-fact-checking-covid-19-news","title":"Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence","date":"2023-05-29","arxiv_id":"2305.18265","n_code_links":1,"syntology":null},{"paper":null,"slug":"coeditor-leveraging-contextual-changes-for","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","date":"2023-05-29","arxiv_id":"2305.18584","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-they-don-t","slug":"do-large-language-models-know-what-they-don-t","title":"Do Large Language Models Know What They Don't Know?","date":"2023-05-29","arxiv_id":"2305.18153","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":["yinzhangyue/selfaware"],"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":"exploring-effectiveness-of-gpt-3-in","title":"Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods","date":"2023-05-29","arxiv_id":"2305.18156","n_code_links":0,"syntology":null},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","n_code_links":1,"syntology":null},{"paper":"/paper/marked-personas-using-natural-language","slug":"marked-personas-using-natural-language","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","date":"2023-05-29","arxiv_id":"2305.18189","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["myracheng/markedpersonas"],"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":"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/syntax-and-semantics-meet-in-the-middle","slug":"syntax-and-semantics-meet-in-the-middle","title":"Syntax and Semantics Meet in the \"Middle\": Probing the Syntax-Semantics Interface of LMs Through Agentivity","date":"2023-05-29","arxiv_id":"2305.18185","n_code_links":1,"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/evaluating-gpt-3-generated-explanations-for","slug":"evaluating-gpt-3-generated-explanations-for","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","date":"2023-05-28","arxiv_id":"2305.17680","n_code_links":1,"syntology":null},{"paper":"/paper/generating-edu-extracts-for-plan-guided","slug":"generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","date":"2023-05-28","arxiv_id":"2305.17779","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":0,"n_instrument":6,"unverified":4,"pointer_only":10,"phrase":"6 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["griff4692/edu-sum"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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":"/paper/kosbi-a-dataset-for-mitigating-social-bias","slug":"kosbi-a-dataset-for-mitigating-social-bias","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","date":"2023-05-28","arxiv_id":"2305.17701","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-label-biases-for-in-context","slug":"mitigating-label-biases-for-in-context","title":"Mitigating Label Biases for In-context Learning","date":"2023-05-28","arxiv_id":"2305.19148","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":["fywalter/label-bias"],"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/square-a-large-scale-dataset-of-sensitive","slug":"square-a-large-scale-dataset-of-sensitive","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","date":"2023-05-28","arxiv_id":"2305.17696","n_code_links":1,"syntology":null},{"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":null,"slug":"complementary-and-integrative-health-lexicon","title":"Complementary and Integrative Health Lexicon (CIHLex) and Entity Recognition in the Literature","date":"2023-05-27","arxiv_id":"2305.17353","n_code_links":0,"syntology":null},{"paper":"/paper/dna-gpt-divergent-n-gram-analysis-for","slug":"dna-gpt-divergent-n-gram-analysis-for","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","date":"2023-05-27","arxiv_id":"2305.17359","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":["xianjun-yang/dna-gpt"],"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/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/towards-explainable-conversational","slug":"towards-explainable-conversational","title":"Towards Explainable Conversational Recommender Systems","date":"2023-05-27","arxiv_id":"2305.18363","n_code_links":1,"syntology":null},{"paper":"/paper/what-can-large-language-models-do-in","slug":"what-can-large-language-models-do-in","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","date":"2023-05-27","arxiv_id":"2305.18365","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":"chatgpt-a-study-on-its-utility-for-ubiquitous","title":"ChatGPT: A Study on its Utility for Ubiquitous Software Engineering Tasks","date":"2023-05-26","arxiv_id":"2305.16837","n_code_links":0,"syntology":null},{"paper":"/paper/counterfactual-reasoning-testing-language","slug":"counterfactual-reasoning-testing-language","title":"Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios","date":"2023-05-26","arxiv_id":"2305.16572","n_code_links":1,"syntology":null},{"paper":null,"slug":"deepseanet-improving-underwater-object","title":"DeepSeaNet: Improving Underwater Object Detection using EfficientDet","date":"2023-05-26","arxiv_id":"2306.06075","n_code_links":0,"syntology":null},{"paper":null,"slug":"distinguishing-human-generated-text-from","title":"Distinguishing Human Generated Text From ChatGPT Generated Text Using Machine Learning","date":"2023-05-26","arxiv_id":"2306.01761","n_code_links":0,"syntology":null},{"paper":"/paper/do-gpts-produce-less-literal-translations","slug":"do-gpts-produce-less-literal-translations","title":"Do GPTs Produce Less Literal Translations?","date":"2023-05-26","arxiv_id":"2305.16806","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-question-generation-needs-more","title":"Evaluation of Question Generation Needs More References","date":"2023-05-26","arxiv_id":"2305.16626","n_code_links":0,"syntology":null},{"paper":null,"slug":"impossible-distillation-from-low-quality","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","date":"2023-05-26","arxiv_id":"2305.16635","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-accuracy-of-gpt-3-4-results-on","title":"Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model","date":"2023-05-26","arxiv_id":"2305.17116","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-as-tool-makers","slug":"large-language-models-as-tool-makers","title":"Large Language Models as Tool Makers","date":"2023-05-26","arxiv_id":"2305.17126","n_code_links":1,"syntology":null},{"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":"playing-repeated-games-with-large-language","title":"Playing repeated games with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16867","n_code_links":0,"syntology":null},{"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":"/paper/landmark-attention-random-access-infinite","slug":"landmark-attention-random-access-infinite","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","date":"2023-05-25","arxiv_id":"2305.16300","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":5,"n_instrument":6,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["epfml/landmark-attention"],"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":["community","listed","official"]}}},{"paper":"/paper/linguistic-properties-of-truthful-response","slug":"linguistic-properties-of-truthful-response","title":"Linguistic Properties of Truthful Response","date":"2023-05-25","arxiv_id":"2305.15875","n_code_links":1,"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":"/paper/a-causal-view-of-entity-bias-in-large","slug":"a-causal-view-of-entity-bias-in-large","title":"A Causal View of Entity Bias in (Large) Language Models","date":"2023-05-24","arxiv_id":"2305.14695","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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luka-group/causal-view-of-entity-bias"],"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":"benchmarking-arabic-ai-with-large-language","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14982","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-questions-training-with-latent","title":"Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering","date":"2023-05-24","arxiv_id":"2305.14901","n_code_links":0,"syntology":null},{"paper":"/paper/chatagri-exploring-potentials-of-chatgpt-on","slug":"chatagri-exploring-potentials-of-chatgpt-on","title":"ChatAgri: Exploring Potentials of ChatGPT on Cross-linguistic Agricultural Text Classification","date":"2023-05-24","arxiv_id":"2305.15024","n_code_links":1,"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/expertprompting-instructing-large-language","slug":"expertprompting-instructing-large-language","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","date":"2023-05-24","arxiv_id":"2305.14688","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["ofa-sys/expertllama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/harnessing-the-power-of-large-language-models","slug":"harnessing-the-power-of-large-language-models","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","date":"2023-05-24","arxiv_id":"2305.15541","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gblackout/logicllama"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"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":null,"slug":"human-centered-metrics-for-dialog-system","title":"Psychological Metrics for Dialog System Evaluation","date":"2023-05-24","arxiv_id":"2305.14757","n_code_links":0,"syntology":null},{"paper":"/paper/i-spy-a-metaphor-large-language-models-and","slug":"i-spy-a-metaphor-large-language-models-and","title":"I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors","date":"2023-05-24","arxiv_id":"2305.14724","n_code_links":1,"syntology":null},{"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":null,"slug":"leveraging-llms-for-kpis-retrieval-from","title":"Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs","date":"2023-05-24","arxiv_id":"2305.16344","n_code_links":0,"syntology":null},{"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":null,"slug":"mastering-the-abcds-of-complex-questions","title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","date":"2023-05-24","arxiv_id":"2305.14750","n_code_links":0,"syntology":null},{"paper":"/paper/peek-across-improving-multi-document-modeling","slug":"peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","date":"2023-05-24","arxiv_id":"2305.15387","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":11,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["aviclu/peekacross"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-checker-plug-and-play-modules-for-fact","slug":"self-checker-plug-and-play-modules-for-fact","title":"Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14623","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":["Miaoranmmm/SelfChecker"],"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/testing-causal-models-of-word-meaning-in-gpt","slug":"testing-causal-models-of-word-meaning-in-gpt","title":"Testing Causal Models of Word Meaning in GPT-3 and -4","date":"2023-05-24","arxiv_id":"2305.14630","n_code_links":1,"syntology":null},{"paper":"/paper/tomchallenges-a-principle-guided-dataset-and","slug":"tomchallenges-a-principle-guided-dataset-and","title":"ToMChallenges: A Principle-Guided Dataset and Diverse Evaluation Tasks for Exploring Theory of Mind","date":"2023-05-24","arxiv_id":"2305.15068","n_code_links":1,"syntology":null},{"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":"/paper/complementing-gpt-3-with-few-shot-sequence-to","slug":"complementing-gpt-3-with-few-shot-sequence-to","title":"Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata","date":"2023-05-23","arxiv_id":"2305.14202","n_code_links":1,"syntology":null},{"paper":null,"slug":"dancing-between-success-and-failure-edit","title":"Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA","date":"2023-05-23","arxiv_id":"2305.14458","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},{"paper":"/paper/dynosaur-a-dynamic-growth-paradigm-for","slug":"dynosaur-a-dynamic-growth-paradigm-for","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","date":"2023-05-23","arxiv_id":"2305.14327","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wadeyin9712/dynosaur"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-open-domain-multi-hop-question","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","date":"2023-05-23","arxiv_id":"2305.13691","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-black-box-few-shot-text","title":"Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation","date":"2023-05-23","arxiv_id":"2305.13785","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-generation-through-summarization","title":"Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control","date":"2023-05-23","arxiv_id":"2305.14459","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-factual-consistency-of-summaries","slug":"evaluating-factual-consistency-of-summaries","title":"Evaluating Factual Consistency of Summaries with Large Language Models","date":"2023-05-23","arxiv_id":"2305.14069","n_code_links":2,"syntology":null},{"paper":"/paper/how-old-is-gpt-the-humbel-framework-for","slug":"how-old-is-gpt-the-humbel-framework-for","title":"HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations","date":"2023-05-23","arxiv_id":"2305.14195","n_code_links":1,"syntology":null},{"paper":null,"slug":"ifqa-a-dataset-for-open-domain-question","title":"IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions","date":"2023-05-23","arxiv_id":"2305.14010","n_code_links":0,"syntology":null},{"paper":"/paper/images-in-language-space-exploring-the","slug":"images-in-language-space-exploring-the","title":"Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks","date":"2023-05-23","arxiv_id":"2305.13782","n_code_links":1,"syntology":null},{"paper":"/paper/instructscore-towards-explainable-text","slug":"instructscore-towards-explainable-text","title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback","date":"2023-05-23","arxiv_id":"2305.14282","n_code_links":2,"syntology":null},{"paper":"/paper/let-s-think-frame-by-frame-evaluating-video","slug":"let-s-think-frame-by-frame-evaluating-video","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","date":"2023-05-23","arxiv_id":"2305.13903","n_code_links":1,"syntology":null},{"paper":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-xl-a-large-scale-dataset-for-long","slug":"narrative-xl-a-large-scale-dataset-for-long","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","date":"2023-05-23","arxiv_id":"2305.13877","n_code_links":1,"syntology":null},{"paper":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-of-language-models-part-1-context","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","date":"2023-05-23","arxiv_id":"2305.13673","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-brain-context-sensitivity-with-masked","title":"Probing Brain Context-Sensitivity with Masked-Attention Generation","date":"2023-05-23","arxiv_id":"2305.13863","n_code_links":0,"syntology":null},{"paper":"/paper/sophia-a-scalable-stochastic-second-order","slug":"sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","arxiv_id":"2305.14342","n_code_links":7,"syntology":{"ran":13,"of":19,"n_ran_checked":12,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/sources-of-hallucination-by-large-language","slug":"sources-of-hallucination-by-large-language","title":"Sources of Hallucination by Large Language Models on Inference Tasks","date":"2023-05-23","arxiv_id":"2305.14552","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-transitive-and-commutative","title":"Training Transitive and Commutative Multimodal Transformers with LoReTTa","date":"2023-05-23","arxiv_id":"2305.14243","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-failures-of-self-consistency-in-the-multi","title":"Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs","date":"2023-05-23","arxiv_id":"2305.14279","n_code_links":0,"syntology":null},{"paper":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["stanford-oval/wikichat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2305-14386","title":"Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation","date":"2023-05-22","arxiv_id":"2305.14386","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-generative-large-language-model","slug":"a-study-of-generative-large-language-model","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","date":"2023-05-22","arxiv_id":"2305.13523","n_code_links":1,"syntology":null},{"paper":"/paper/can-large-language-models-emulate-an","slug":"can-large-language-models-emulate-an","title":"Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model","date":"2023-05-22","arxiv_id":"2305.13014","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-facilitate-interpretation-of-pre","title":"Can LLMs facilitate interpretation of pre-trained language models?","date":"2023-05-22","arxiv_id":"2305.13386","n_code_links":0,"syntology":null}],"record_sha256":"ef6808042470077992bba7d4c9c9e97132faae7098fa6b61330103eb6fa94448","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}