{"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/adam/papers/127","list_of":"/method/adam","method":"Adam","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":127,"pages_in_order":244,"rows_per_page":100,"rows":[12601,12700],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/126","next":"/method/adam/papers/128","papers":[{"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":"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/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":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-xl-a-large-scale-dataset-for-long","slug":"narrative-xl-a-large-scale-dataset-for-long","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","date":"2023-05-23","arxiv_id":"2305.13877","n_code_links":1,"syntology":null},{"paper":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","n_code_links":1,"syntology":null},{"paper":null,"slug":"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":"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":"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":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/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":"/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":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/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":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":null,"slug":"training-transitive-and-commutative","title":"Training Transitive and Commutative Multimodal Transformers with LoReTTa","date":"2023-05-23","arxiv_id":"2305.14243","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-failures-of-self-consistency-in-the-multi","title":"Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs","date":"2023-05-23","arxiv_id":"2305.14279","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-and-improving-optimization-in","slug":"understanding-and-improving-optimization-in","title":"Understanding and Improving Optimization in Predictive Coding Networks","date":"2023-05-23","arxiv_id":"2305.13562","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":null,"slug":"2305-14386","title":"Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation","date":"2023-05-22","arxiv_id":"2305.14386","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-of-generative-large-language-model","slug":"a-study-of-generative-large-language-model","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","date":"2023-05-22","arxiv_id":"2305.13523","n_code_links":1,"syntology":null},{"paper":null,"slug":"adaptive-action-supervision-in-reinforcement","title":"Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations","date":"2023-05-22","arxiv_id":"2305.13030","n_code_links":0,"syntology":null},{"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":"/paper/can-large-language-models-emulate-an","slug":"can-large-language-models-emulate-an","title":"Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model","date":"2023-05-22","arxiv_id":"2305.13014","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-facilitate-interpretation-of-pre","title":"Can LLMs facilitate interpretation of pre-trained language models?","date":"2023-05-22","arxiv_id":"2305.13386","n_code_links":0,"syntology":null},{"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/communication-minimizing-asynchronous-tensor","slug":"communication-minimizing-asynchronous-tensor","title":"A 4D Hybrid Algorithm to Scale Parallel Training to Thousands of GPUs","date":"2023-05-22","arxiv_id":"2305.13525","n_code_links":1,"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":"/paper/flover-a-temporal-fusion-framework-for","slug":"flover-a-temporal-fusion-framework-for","title":"Flover: A Temporal Fusion Framework for Efficient Autoregressive Model Parallel Inference","date":"2023-05-22","arxiv_id":"2305.13484","n_code_links":1,"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":"gatology-for-linguistics-what-syntactic","title":"GATology for Linguistics: What Syntactic Dependencies It Knows","date":"2023-05-22","arxiv_id":"2305.13403","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":null,"slug":"imsimcse-improving-contrastive-learning-for","title":"SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives","date":"2023-05-22","arxiv_id":"2305.13192","n_code_links":0,"syntology":null},{"paper":null,"slug":"inheritsumm-a-general-versatile-and-compact","title":"InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT","date":"2023-05-22","arxiv_id":"2305.13083","n_code_links":0,"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":"/paper/language-agnostic-bias-detection-in-language","slug":"language-agnostic-bias-detection-in-language","title":"Language-Agnostic Bias Detection in Language Models with Bias Probing","date":"2023-05-22","arxiv_id":"2305.13302","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":"/paper/logical-reasoning-for-natural-language","slug":"logical-reasoning-for-natural-language","title":"Atomic Inference for NLI with Generated Facts as Atoms","date":"2023-05-22","arxiv_id":"2305.13214","n_code_links":1,"syntology":null},{"paper":"/paper/mailex-email-event-and-argument-extraction","slug":"mailex-email-event-and-argument-extraction","title":"MAILEX: Email Event and Argument Extraction","date":"2023-05-22","arxiv_id":"2305.13469","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-inductive-biases-of-in-context","slug":"measuring-inductive-biases-of-in-context","title":"Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations","date":"2023-05-22","arxiv_id":"2305.13299","n_code_links":1,"syntology":null},{"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":"/paper/nndetection-for-intracranial-aneurysms","slug":"nndetection-for-intracranial-aneurysms","title":"nnDetection for Intracranial Aneurysms Detection and Localization","date":"2023-05-22","arxiv_id":"2305.13398","n_code_links":1,"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":"the-emergence-of-economic-rationality-of-gpt","title":"The Emergence of Economic Rationality of GPT","date":"2023-05-22","arxiv_id":"2305.12763","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},{"paper":null,"slug":"towards-dialogue-systems-with-agency-in-human","title":"Investigating Agency of LLMs in Human-AI Collaboration Tasks","date":"2023-05-22","arxiv_id":"2305.12815","n_code_links":0,"syntology":null},{"paper":"/paper/vdt-an-empirical-study-on-video-diffusion","slug":"vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","arxiv_id":"2305.13311","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":4,"n_instrument":4,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rerv/vdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/videollm-modeling-video-sequence-with-large","slug":"videollm-modeling-video-sequence-with-large","title":"VideoLLM: Modeling Video Sequence with Large Language Models","date":"2023-05-22","arxiv_id":"2305.13292","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-current-rain-denoising-models-fail-on","title":"Why current rain denoising models fail on CycleGAN created rain images in autonomous driving","date":"2023-05-22","arxiv_id":"2305.12983","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deeper-autoregressive-approach-to-non","title":"A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsing","date":"2023-05-21","arxiv_id":"2305.12510","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-symbolic-framework-for-systematic","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","date":"2023-05-21","arxiv_id":"2305.12563","n_code_links":0,"syntology":null},{"paper":"/paper/bertrlfuzzer-a-bert-and-reinforcement","slug":"bertrlfuzzer-a-bert-and-reinforcement","title":"BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer","date":"2023-05-21","arxiv_id":"2305.12534","n_code_links":1,"syntology":null},{"paper":"/paper/biasasker-measuring-the-bias-in","slug":"biasasker-measuring-the-bias-in","title":"BiasAsker: Measuring the Bias in Conversational AI System","date":"2023-05-21","arxiv_id":"2305.12434","n_code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-with-logic-driven-data","slug":"contrastive-learning-with-logic-driven-data","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","date":"2023-05-21","arxiv_id":"2305.12599","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-performance-of-large-language","slug":"evaluating-the-performance-of-large-language","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","date":"2023-05-21","arxiv_id":"2305.12474","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":["openlmlab/gaokao-bench"],"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"]}}}],"record_sha256":"75506bb2d6725cff6847f7b6b4408c1793f7d89b61d9c3407c81b7969444f85b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}