{"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/attention-dropout/papers/53","list_of":"/method/attention-dropout","method":"Attention Dropout","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":53,"pages_in_order":109,"rows_per_page":100,"rows":[5201,5300],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/attention-dropout","prev":"/method/attention-dropout/papers/52","next":"/method/attention-dropout/papers/54","papers":[{"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/modeling-adversarial-attack-on-pre-trained","slug":"modeling-adversarial-attack-on-pre-trained","title":"Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making","date":"2023-05-27","arxiv_id":"2305.17440","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/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","n_code_links":2,"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":{"repos":["zoeyyao27/graph-of-thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"calibration-of-transformer-based-models-for","title":"Calibration of Transformer-based Models for Identifying Stress and Depression in Social Media","date":"2023-05-26","arxiv_id":"2305.16797","n_code_links":0,"syntology":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":"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":"/paper/geovln-learning-geometry-enhanced-visual-1","slug":"geovln-learning-geometry-enhanced-visual-1","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","date":"2023-05-26","arxiv_id":"2305.17102","n_code_links":1,"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":null,"slug":"incorporating-distributions-of-discourse","title":"Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization","date":"2023-05-26","arxiv_id":"2305.16784","n_code_links":0,"syntology":null},{"paper":null,"slug":"knse-a-knowledge-aware-natural-language","title":"KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status Recognition","date":"2023-05-26","arxiv_id":"2305.16833","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/learning-to-imagine-visually-augmented","slug":"learning-to-imagine-visually-augmented","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","date":"2023-05-26","arxiv_id":"2305.16944","n_code_links":1,"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":["rucaibox/live"],"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/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":"theoretical-and-practical-perspectives-on","title":"Theoretical and Practical Perspectives on what Influence Functions Do","date":"2023-05-26","arxiv_id":"2305.16971","n_code_links":0,"syntology":null},{"paper":"/paper/zero-is-not-hero-yet-benchmarking-zero-shot","slug":"zero-is-not-hero-yet-benchmarking-zero-shot","title":"Zero is Not Hero Yet: Benchmarking Zero-Shot Performance of LLMs for Financial Tasks","date":"2023-05-26","arxiv_id":"2305.16633","n_code_links":1,"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":null,"slug":"comparative-study-of-pre-trained-bert-models","title":"Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data","date":"2023-05-25","arxiv_id":"2305.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-attention-layers-coupled-with","title":"Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech","date":"2023-05-25","arxiv_id":"2305.16406","n_code_links":0,"syntology":null},{"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/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/text-to-motion-retrieval-towards-joint","slug":"text-to-motion-retrieval-towards-joint","title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language","date":"2023-05-25","arxiv_id":"2305.15842","n_code_links":1,"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":"/paper/complex-mathematical-symbol-definition","slug":"complex-mathematical-symbol-definition","title":"Complex Mathematical Symbol Definition Structures: A Dataset and Model for Coordination Resolution in Definition Extraction","date":"2023-05-24","arxiv_id":"2305.14660","n_code_links":1,"syntology":null},{"paper":"/paper/context-aware-transformer-pre-training-for","slug":"context-aware-transformer-pre-training-for","title":"Context-Aware Transformer Pre-Training for Answer Sentence Selection","date":"2023-05-24","arxiv_id":"2305.15358","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":null,"slug":"dynamic-masking-rate-schedules-for-mlm","title":"Dynamic Masking Rate Schedules for MLM Pretraining","date":"2023-05-24","arxiv_id":"2305.15096","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":null,"slug":"extracting-psychological-indicators-using","title":"Extracting Psychological Indicators Using Question Answering","date":"2023-05-24","arxiv_id":"2305.14891","n_code_links":0,"syntology":null},{"paper":"/paper/ghostbuster-detecting-text-ghostwritten-by","slug":"ghostbuster-detecting-text-ghostwritten-by","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","date":"2023-05-24","arxiv_id":"2305.15047","n_code_links":2,"syntology":null},{"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":"/paper/how-to-distill-your-bert-an-empirical-study","slug":"how-to-distill-your-bert-an-empirical-study","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","date":"2023-05-24","arxiv_id":"2305.15032","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mainlp/how-to-distill-your-bert"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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":null,"slug":"neural-summarization-of-electronic-health","title":"Neural Summarization of Electronic Health Records","date":"2023-05-24","arxiv_id":"2305.15222","n_code_links":0,"syntology":null},{"paper":"/paper/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/revisiting-token-dropping-strategy-in","slug":"revisiting-token-dropping-strategy-in","title":"Revisiting Token Dropping Strategy in Efficient BERT Pretraining","date":"2023-05-24","arxiv_id":"2305.15273","n_code_links":1,"syntology":null},{"paper":"/paper/segmented-recurrent-transformer-an-efficient","slug":"segmented-recurrent-transformer-an-efficient","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","date":"2023-05-24","arxiv_id":"2305.16340","n_code_links":1,"syntology":null},{"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":"2305-14521","title":"Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings","date":"2023-05-23","arxiv_id":"2305.14521","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-method-for-unsupervised-bilingual","slug":"a-simple-method-for-unsupervised-bilingual","title":"When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages","date":"2023-05-23","arxiv_id":"2305.14012","n_code_links":1,"syntology":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/all-roads-lead-to-rome-exploring-the","slug":"all-roads-lead-to-rome-exploring-the","title":"All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations","date":"2023-05-23","arxiv_id":"2305.14555","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["twinkle0331/bert-similarity"],"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":"assessing-linguistic-generalisation-in","title":"Assessing Linguistic Generalisation in Language Models: A Dataset for Brazilian Portuguese","date":"2023-05-23","arxiv_id":"2305.14070","n_code_links":0,"syntology":null},{"paper":"/paper/axomiyaberta-a-phonologically-aware","slug":"axomiyaberta-a-phonologically-aware","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","date":"2023-05-23","arxiv_id":"2305.13641","n_code_links":1,"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":"/paper/connecting-the-dots-what-graph-based-text","slug":"connecting-the-dots-what-graph-based-text","title":"Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification Using Graph Neural Networks?","date":"2023-05-23","arxiv_id":"2305.14578","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/exploring-large-language-models-for-classical","slug":"exploring-large-language-models-for-classical","title":"Exploring Large Language Models for Classical Philology","date":"2023-05-23","arxiv_id":"2305.13698","n_code_links":1,"syntology":null},{"paper":null,"slug":"grace-generation-using-associated-code-edits","title":"GrACE: Generation using Associated Code Edits","date":"2023-05-23","arxiv_id":"2305.14129","n_code_links":0,"syntology":null},{"paper":null,"slug":"handling-realistic-label-noise-in-bert-text","title":"Handling Realistic Label Noise in BERT Text Classification","date":"2023-05-23","arxiv_id":"2305.16337","n_code_links":0,"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":"mmt5-modular-multilingual-pre-training-solves","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","date":"2023-05-23","arxiv_id":"2305.14224","n_code_links":0,"syntology":null},{"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":"/paper/text-is-all-you-need-learning-language","slug":"text-is-all-you-need-learning-language","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","date":"2023-05-23","arxiv_id":"2305.13731","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":null}},{"paper":"/paper/towards-massively-multi-domain-multilingual","slug":"towards-massively-multi-domain-multilingual","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","date":"2023-05-23","arxiv_id":"2305.14463","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}],"record_sha256":"b612a5490245c03129e0c604581f2683ae30d72ed39d026ff049621ca7b49bc2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}