{"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/softmax/papers/213","list_of":"/method/softmax","method":"Softmax","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":213,"pages_in_order":375,"rows_per_page":100,"rows":[21201,21300],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/212","next":"/method/softmax/papers/214","papers":[{"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":"/paper/bytesized32-a-corpus-and-challenge-task-for","slug":"bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","date":"2023-05-24","arxiv_id":"2305.14879","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["cognitiveailab/bytesized32"],"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":"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":"clever-hans-or-neural-theory-of-mind-stress","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","date":"2023-05-24","arxiv_id":"2305.14763","n_code_links":0,"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":"diffusion-models-in-nlp-a-survey-1","title":"A Survey of Diffusion Models in Natural Language Processing","date":"2023-05-24","arxiv_id":"2305.14671","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/fourier-transformer-fast-long-range-modeling","slug":"fourier-transformer-fast-long-range-modeling","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","date":"2023-05-24","arxiv_id":"2305.15099","n_code_links":1,"syntology":null},{"paper":"/paper/from-words-to-wires-generating-functioning","slug":"from-words-to-wires-generating-functioning","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","date":"2023-05-24","arxiv_id":"2305.14874","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":["cognitiveailab/words2wires"],"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/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/gorilla-large-language-model-connected-with","slug":"gorilla-large-language-model-connected-with","title":"Gorilla: Large Language Model Connected with Massive APIs","date":"2023-05-24","arxiv_id":"2305.15334","n_code_links":1,"syntology":null},{"paper":null,"slug":"gptaraeval-a-comprehensive-evaluation-of","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","date":"2023-05-24","arxiv_id":"2305.14976","n_code_links":0,"syntology":null},{"paper":null,"slug":"gtnet-graph-transformer-network-for-3d-point","title":"GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation","date":"2023-05-24","arxiv_id":"2305.15213","n_code_links":0,"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":"/paper/huatuogpt-towards-taming-language-model-to-be","slug":"huatuogpt-towards-taming-language-model-to-be","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","date":"2023-05-24","arxiv_id":"2305.15075","n_code_links":2,"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":["freedomintelligence/huatuogpt"],"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":"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/improving-selective-classification","slug":"improving-selective-classification","title":"How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks","date":"2023-05-24","arxiv_id":"2305.15508","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lfpc/fixselectiveclassification"],"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/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":"interformer-interactive-local-and-global","title":"InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition","date":"2023-05-24","arxiv_id":"2305.16342","n_code_links":0,"syntology":null},{"paper":"/paper/is-gpt-4-a-good-data-analyst","slug":"is-gpt-4-a-good-data-analyst","title":"Is GPT-4 a Good Data Analyst?","date":"2023-05-24","arxiv_id":"2305.15038","n_code_links":1,"syntology":null},{"paper":"/paper/just-ask-for-calibration-strategies-for","slug":"just-ask-for-calibration-strategies-for","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","date":"2023-05-24","arxiv_id":"2305.14975","n_code_links":1,"syntology":null},{"paper":null,"slug":"knn-lm-does-not-improve-open-ended-text","title":"KNN-LM Does Not Improve Open-ended Text Generation","date":"2023-05-24","arxiv_id":"2305.14625","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-effective-table-to","slug":"large-language-models-are-effective-table-to","title":"Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios","date":"2023-05-24","arxiv_id":"2305.14987","n_code_links":2,"syntology":null},{"paper":null,"slug":"leveraging-gpt-4-for-automatic-translation","title":"Leveraging GPT-4 for Automatic Translation Post-Editing","date":"2023-05-24","arxiv_id":"2305.14878","n_code_links":0,"syntology":null},{"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":null,"slug":"leveraging-pre-trained-large-language-models","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","date":"2023-05-24","arxiv_id":"2305.14909","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":"multi-modal-mutual-attention-and-iterative","title":"Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation","date":"2023-05-24","arxiv_id":"2305.15302","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiresolution-feature-guidance-based","title":"Multiresolution Feature Guidance Based Transformer for Anomaly Detection","date":"2023-05-24","arxiv_id":"2305.14880","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":null,"slug":"p-vectors-a-parallel-coupled-tdnn-transformer","title":"P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification","date":"2023-05-24","arxiv_id":"2305.14778","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/pre-rmsnorm-and-pre-crmsnorm-transformers","slug":"pre-rmsnorm-and-pre-crmsnorm-transformers","title":"Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers","date":"2023-05-24","arxiv_id":"2305.14858","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["zixuanjiang/pre-rmsnorm-transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"predicting-token-impact-towards-efficient","title":"Predicting Token Impact Towards Efficient Vision Transformer","date":"2023-05-24","arxiv_id":"2305.14840","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["owaski/autoplan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/reasoning-with-language-model-is-planning","slug":"reasoning-with-language-model-is-planning","title":"Reasoning with Language Model is Planning with World Model","date":"2023-05-24","arxiv_id":"2305.14992","n_code_links":3,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/refgpt-reference-truthful-customized","slug":"refgpt-reference-truthful-customized","title":"RefGPT: Dialogue Generation of GPT, by GPT, and for GPT","date":"2023-05-24","arxiv_id":"2305.14994","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-finetuned-vision-code","title":"Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering","date":"2023-05-24","arxiv_id":"2305.14637","n_code_links":0,"syntology":null},{"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/selfood-self-supervised-out-of-distribution","slug":"selfood-self-supervised-out-of-distribution","title":"SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank","date":"2023-05-24","arxiv_id":"2305.14696","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":["dheeraj7596/selfood"],"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/semi-supervised-and-long-tailed-object","slug":"semi-supervised-and-long-tailed-object","title":"Semi-Supervised and Long-Tailed Object Detection with CascadeMatch","date":"2023-05-24","arxiv_id":"2305.14813","n_code_links":1,"syntology":null},{"paper":"/paper/spring-gpt-4-out-performs-rl-algorithms-by","slug":"spring-gpt-4-out-performs-rl-algorithms-by","title":"SPRING: Studying the Paper and Reasoning to Play Games","date":"2023-05-24","arxiv_id":"2305.15486","n_code_links":1,"syntology":null},{"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":null,"slug":"towards-adaptive-prefix-tuning-for-parameter","title":"Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning","date":"2023-05-24","arxiv_id":"2305.15212","n_code_links":0,"syntology":null},{"paper":"/paper/towards-reliable-misinformation-mitigation","slug":"towards-reliable-misinformation-mitigation","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","date":"2023-05-24","arxiv_id":"2305.14928","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":["complexdata-mila/mitigatemisinfo"],"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":"/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/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":2,"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":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/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/aligning-large-language-models-through","slug":"aligning-large-language-models-through","title":"Aligning Large Language Models through Synthetic Feedback","date":"2023-05-23","arxiv_id":"2305.13735","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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["naver-ai/almost"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/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":"analog-implementation-of-the-softmax-function","title":"Analog Implementation of the Softmax Function","date":"2023-05-23","arxiv_id":"2305.13649","n_code_links":0,"syntology":null},{"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":null,"slug":"attentive-continuous-generative-self-training","title":"Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation","date":"2023-05-23","arxiv_id":"2305.14589","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","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":["xuzhao0/model-selection-reasoning"],"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/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":null,"slug":"causal-intervention-for-abstractive-related","title":"Causal Intervention for Abstractive Related Work Generation","date":"2023-05-23","arxiv_id":"2305.13685","n_code_links":0,"syntology":null},{"paper":"/paper/cgce-a-chinese-generative-chat-evaluation","slug":"cgce-a-chinese-generative-chat-evaluation","title":"CGCE: A Chinese Generative Chat Evaluation Benchmark for General and Financial Domains","date":"2023-05-23","arxiv_id":"2305.14471","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/condensing-multilingual-knowledge-with","slug":"condensing-multilingual-knowledge-with","title":"Condensing Multilingual Knowledge with Lightweight Language-Specific Modules","date":"2023-05-23","arxiv_id":"2305.13993","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 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["fe1ixxu/lms_fd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"/paper/cross-attention-is-not-enough-incongruity","slug":"cross-attention-is-not-enough-incongruity","title":"Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition","date":"2023-05-23","arxiv_id":"2305.13583","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":null,"slug":"detecting-automatically-the-layout-of","title":"Detecting automatically the layout of clinical documents to enhance the performances of downstream natural language processing","date":"2023-05-23","arxiv_id":"2305.13817","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":"eeg2vec-self-supervised","title":"Eeg2vec: Self-Supervised Electroencephalographic Representation Learning","date":"2023-05-23","arxiv_id":"2305.13957","n_code_links":0,"syntology":null},{"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":"/paper/empowering-llm-based-machine-translation-with","slug":"empowering-llm-based-machine-translation-with","title":"Benchmarking Machine Translation with Cultural Awareness","date":"2023-05-23","arxiv_id":"2305.14328","n_code_links":1,"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":"/paper/factscore-fine-grained-atomic-evaluation-of","slug":"factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","arxiv_id":"2305.14251","n_code_links":4,"syntology":{"ran":11,"of":15,"n_ran_checked":10,"n_instrument":1,"unverified":4,"pointer_only":6,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shmsw25/factscore"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"from-characters-to-words-hierarchical-pre","title":"From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding","date":"2023-05-23","arxiv_id":"2305.14571","n_code_links":0,"syntology":null},{"paper":null,"slug":"genspectrum-chat-data-exploration-in-public","title":"GenSpectrum Chat: Data Exploration in Public Health Using Large Language Models","date":"2023-05-23","arxiv_id":"2305.13821","n_code_links":0,"syntology":null},{"paper":"/paper/goat-fine-tuned-llama-outperforms-gpt-4-on","slug":"goat-fine-tuned-llama-outperforms-gpt-4-on","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","date":"2023-05-23","arxiv_id":"2305.14201","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}],"record_sha256":"24fd800b715c03c10f87c95c2510e28b30e24f3250361ade3e476a23055c4851","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}