{"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/position-wise-feed-forward-layer/papers/81","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","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":81,"pages_in_order":139,"rows_per_page":100,"rows":[8001,8100],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/80","next":"/method/position-wise-feed-forward-layer/papers/82","papers":[{"paper":"/paper/unitrec-a-unified-text-to-text-transformer","slug":"unitrec-a-unified-text-to-text-transformer","title":"UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation","date":"2023-05-25","arxiv_id":"2305.15756","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["veason-silverbullet/unitrec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"viola-unified-codec-language-models-for","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","date":"2023-05-25","arxiv_id":"2305.16107","n_code_links":0,"syntology":null},{"paper":"/paper/voyager-an-open-ended-embodied-agent-with","slug":"voyager-an-open-ended-embodied-agent-with","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","date":"2023-05-25","arxiv_id":"2305.16291","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["MineDojo/Voyager"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/2305-14649","slug":"2305-14649","title":"A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting","date":"2023-05-24","arxiv_id":"2305.14649","n_code_links":1,"syntology":null},{"paper":"/paper/2305-14675","slug":"2305-14675","title":"TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation","date":"2023-05-24","arxiv_id":"2305.14675","n_code_links":1,"syntology":null},{"paper":"/paper/a-new-era-in-software-security-towards-self","slug":"a-new-era-in-software-security-towards-self","title":"A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification","date":"2023-05-24","arxiv_id":"2305.14752","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-relentless-benchmark-for-modelling-graded","title":"A RelEntLess Benchmark for Modelling Graded Relations between Named Entities","date":"2023-05-24","arxiv_id":"2305.15002","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-demonstration-attacks-on-large","title":"Adversarial Demonstration Attacks on Large Language Models","date":"2023-05-24","arxiv_id":"2305.14950","n_code_links":0,"syntology":null},{"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":"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":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":"/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/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/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":"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":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":"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/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/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":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/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/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/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":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/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/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":"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":"/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":"/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":"/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/learning-to-generate-novel-scientific","slug":"learning-to-generate-novel-scientific","title":"SciMON: Scientific Inspiration Machines Optimized for Novelty","date":"2023-05-23","arxiv_id":"2305.14259","n_code_links":1,"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/llm-powered-data-augmentation-for-enhanced","slug":"llm-powered-data-augmentation-for-enhanced","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","date":"2023-05-23","arxiv_id":"2305.14288","n_code_links":1,"syntology":null},{"paper":"/paper/llms-as-factual-reasoners-insights-from","slug":"llms-as-factual-reasoners-insights-from","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","date":"2023-05-23","arxiv_id":"2305.14540","n_code_links":1,"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":null,"slug":"on-structural-expressive-power-of-graph","title":"On Structural Expressive Power of Graph Transformers","date":"2023-05-23","arxiv_id":"2305.13987","n_code_links":0,"syntology":null},{"paper":"/paper/patch-mix-contrastive-learning-with-audio","slug":"patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","arxiv_id":"2305.14032","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["raymin0223/patch-mix_contrastive_learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pre-training-multi-task-contrastive-learning","title":"Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding","date":"2023-05-23","arxiv_id":"2305.14232","n_code_links":0,"syntology":null},{"paper":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","n_code_links":20,"syntology":{"ran":18,"of":26,"n_ran_checked":6,"n_instrument":12,"unverified":8,"pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"paper":null,"slug":"rethinking-speech-recognition-with-a","title":"Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding","date":"2023-05-23","arxiv_id":"2305.14049","n_code_links":0,"syntology":null},{"paper":null,"slug":"source-free-domain-adaptation-for-rgb-d","title":"Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers","date":"2023-05-23","arxiv_id":"2305.14269","n_code_links":0,"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":null,"slug":"towards-a-unified-view-of-sparse-feed-forward","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model","date":"2023-05-23","arxiv_id":"2305.13999","n_code_links":0,"syntology":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":"/paper/vdd-varied-drone-dataset-for-semantic","slug":"vdd-varied-drone-dataset-for-semantic","title":"VDD: Varied Drone Dataset for Semantic Segmentation","date":"2023-05-23","arxiv_id":"2305.13608","n_code_links":1,"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":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long","slug":"zeroscrolls-a-zero-shot-benchmark-for-long","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","date":"2023-05-23","arxiv_id":"2305.14196","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tau-nlp/zero_scrolls"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/are-large-language-models-good-evaluators-for","slug":"are-large-language-models-good-evaluators-for","title":"Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization","date":"2023-05-22","arxiv_id":"2305.13091","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":["damo-nlp-sg/llm_summeval"],"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/beneath-surface-similarity-large-language","slug":"beneath-surface-similarity-large-language","title":"Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction","date":"2023-05-22","arxiv_id":"2305.12660","n_code_links":1,"syntology":null},{"paper":"/paper/bidirectional-transformer-reranker-for","slug":"bidirectional-transformer-reranker-for","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","date":"2023-05-22","arxiv_id":"2305.13000","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-chatgpt-defend-the-truth-automatic","title":"Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate","date":"2023-05-22","arxiv_id":"2305.13160","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognitive-network-science-reveals-bias-in-gpt","title":"Cognitive network science reveals bias in GPT-3, ChatGPT, and GPT-4 mirroring math anxiety in high-school students","date":"2023-05-22","arxiv_id":"2305.18320","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-and-enhancing-structural","slug":"evaluating-and-enhancing-structural","title":"Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study","date":"2023-05-22","arxiv_id":"2305.13062","n_code_links":1,"syntology":null},{"paper":"/paper/explaincpe-a-free-text-explanation-benchmark","slug":"explaincpe-a-free-text-explanation-benchmark","title":"ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination","date":"2023-05-22","arxiv_id":"2305.12945","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-energy-based-language-models-with","slug":"exploring-energy-based-language-models-with","title":"Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition","date":"2023-05-22","arxiv_id":"2305.12676","n_code_links":2,"syntology":null},{"paper":null,"slug":"g3detector-general-gpt-generated-text","title":"G3Detector: General GPT-Generated Text Detector","date":"2023-05-22","arxiv_id":"2305.12680","n_code_links":0,"syntology":null},{"paper":null,"slug":"gncformer-enhanced-self-attention-for","title":"GNCformer Enhanced Self-attention for Automatic Speech Recognition","date":"2023-05-22","arxiv_id":"2305.12755","n_code_links":0,"syntology":null},{"paper":"/paper/how-language-model-hallucinations-can","slug":"how-language-model-hallucinations-can","title":"How Language Model Hallucinations Can Snowball","date":"2023-05-22","arxiv_id":"2305.13534","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-forward-tuning-boosts-in-context","slug":"iterative-forward-tuning-boosts-in-context","title":"Iterative Forward Tuning Boosts In-Context Learning in Language Models","date":"2023-05-22","arxiv_id":"2305.13016","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-pedestrian-actions-to-ensure-safe","title":"Learning Pedestrian Actions to Ensure Safe Autonomous Driving","date":"2023-05-22","arxiv_id":"2305.13051","n_code_links":0,"syntology":null},{"paper":"/paper/learning-subpocket-prototypes-for","slug":"learning-subpocket-prototypes-for","title":"Learning Subpocket Prototypes for Generalizable Structure-based Drug Design","date":"2023-05-22","arxiv_id":"2305.13997","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["zaixizhang/flag"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/llms-for-knowledge-graph-construction-and","slug":"llms-for-knowledge-graph-construction-and","title":"LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities","date":"2023-05-22","arxiv_id":"2305.13168","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["zjunlp/autokg"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"multi-task-instruction-tuning-of-llama-for","title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","date":"2023-05-22","arxiv_id":"2305.13225","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-attention-and-feed-forward-net","title":"Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design","date":"2023-05-22","arxiv_id":"2305.13297","n_code_links":0,"syntology":null},{"paper":"/paper/recurrentgpt-interactive-generation-of","slug":"recurrentgpt-interactive-generation-of","title":"RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text","date":"2023-05-22","arxiv_id":"2305.13304","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aiwaves-cn/recurrentgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/rwkv-reinventing-rnns-for-the-transformer-era","slug":"rwkv-reinventing-rnns-for-the-transformer-era","title":"RWKV: Reinventing RNNs for the Transformer Era","date":"2023-05-22","arxiv_id":"2305.13048","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["BlinkDL/RWKV-LM","blinkdl/chatrwkv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/scitab-a-challenging-benchmark-for","slug":"scitab-a-challenging-benchmark-for","title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","date":"2023-05-22","arxiv_id":"2305.13186","n_code_links":1,"syntology":null},{"paper":null,"slug":"stock-and-market-index-prediction-using","title":"Stock and market index prediction using Informer network","date":"2023-05-22","arxiv_id":"2305.14382","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntactic-knowledge-via-graph-attention-with","title":"Syntactic Knowledge via Graph Attention with BERT in Machine Translation","date":"2023-05-22","arxiv_id":"2305.13413","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenized-graph-transformer-with-neighborhood","title":"Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs","date":"2023-05-22","arxiv_id":"2305.12677","n_code_links":0,"syntology":null}],"record_sha256":"bba7538ebd5debcd65b9fb18177544ce2491f8ddb321b1c2acab4ced46e8e92b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}