{"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/layer-normalization/papers/135","list_of":"/method/layer-normalization","method":"Layer Normalization","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":135,"pages_in_order":250,"rows_per_page":100,"rows":[13401,13500],"of":24980,"counts":{"archive_papers_tagged":24980,"with_a_code_link":11273,"where_syntology_ran_a_sample":3471,"not_listed_spam_title":0,"listed":24980,"listed_where_code_ran":3471,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2923,"every_run_a_failure_of_syntologys_instrument":548,"listed_with_a_run_with_no_instrument_failure":2923,"listed_every_run_a_failure_of_syntologys_instrument":548,"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/layer-normalization","prev":"/method/layer-normalization/papers/134","next":"/method/layer-normalization/papers/136","papers":[{"paper":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mmt5-modular-multilingual-pre-training-solves","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","date":"2023-05-23","arxiv_id":"2305.14224","n_code_links":0,"syntology":null},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-xl-a-large-scale-dataset-for-long","slug":"narrative-xl-a-large-scale-dataset-for-long","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","date":"2023-05-23","arxiv_id":"2305.13877","n_code_links":1,"syntology":null},{"paper":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","n_code_links":1,"syntology":null},{"paper":null,"slug":"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/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/weakly-supervised-3d-open-vocabulary-1","slug":"weakly-supervised-3d-open-vocabulary-1","title":"Weakly Supervised 3D Open-vocabulary Segmentation","date":"2023-05-23","arxiv_id":"2305.14093","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":10,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"12 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kunhao-liu/3d-ovs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"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":"/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/deepjscc-l-robust-and-bandwidth-adaptive","slug":"deepjscc-l-robust-and-bandwidth-adaptive","title":"DeepJSCC-l++: Robust and Bandwidth-Adaptive Wireless Image Transmission","date":"2023-05-22","arxiv_id":"2305.13161","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-large-scale-vision-representation","title":"Efficient Large-Scale Visual Representation Learning And Evaluation","date":"2023-05-22","arxiv_id":"2305.13399","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":"/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":null,"slug":"materialistic-selecting-similar-materials-in","title":"Materialistic: Selecting Similar Materials in Images","date":"2023-05-22","arxiv_id":"2305.13291","n_code_links":0,"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":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":"/paper/sparsefit-few-shot-prompting-with-sparse-fine","slug":"sparsefit-few-shot-prompting-with-sparse-fine","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","date":"2023-05-22","arxiv_id":"2305.13235","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatiotemporal-attention-based-semantic","title":"Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition","date":"2023-05-22","arxiv_id":"2305.12796","n_code_links":0,"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":null,"slug":"tsptq-vit-two-scaled-post-training","title":"TSPTQ-ViT: Two-scaled post-training quantization for vision transformer","date":"2023-05-22","arxiv_id":"2305.12901","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"]}}},{"paper":"/paper/explaining-how-transformers-use-context-to","slug":"explaining-how-transformers-use-context-to","title":"Explaining How Transformers Use Context to Build Predictions","date":"2023-05-21","arxiv_id":"2305.12535","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":8,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"9 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mt-upc/logit-explanations"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"f-pabee-flexible-patience-based-early-exiting","title":"F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks","date":"2023-05-21","arxiv_id":"2305.11916","n_code_links":0,"syntology":null},{"paper":"/paper/gene-set-summarization-using-large-language","slug":"gene-set-summarization-using-large-language","title":"Gene Set Summarization using Large Language Models","date":"2023-05-21","arxiv_id":"2305.13338","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["monarch-initiative/talisman"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-3-5-vs-gpt-4-evaluating-chatgpt-s","title":"GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts","date":"2023-05-21","arxiv_id":"2305.12477","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-paternity-test-gpt-generated-text","title":"DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection","date":"2023-05-21","arxiv_id":"2305.12519","n_code_links":0,"syntology":null},{"paper":null,"slug":"hiint-historical-intra-and-inter-personal","title":"HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer","date":"2023-05-21","arxiv_id":"2305.12369","n_code_links":0,"syntology":null},{"paper":null,"slug":"infor-coef-information-bottleneck-based","title":"Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model","date":"2023-05-21","arxiv_id":"2305.12458","n_code_links":0,"syntology":null},{"paper":null,"slug":"ir-models-and-the-covid-19-pandemic-a","title":"IR Models and the COVID-19 Pandemic: A Comparative Study of Performance and Challenges","date":"2023-05-21","arxiv_id":"2305.12528","n_code_links":0,"syntology":null},{"paper":"/paper/learning-joint-2d-3d-diffusion-models-for","slug":"learning-joint-2d-3d-diffusion-models-for","title":"Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation","date":"2023-05-21","arxiv_id":"2305.12347","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"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) · 1 unverified","official":{"repos":["graph-0/jodo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/model-generated-pretraining-signals-improves","slug":"model-generated-pretraining-signals-improves","title":"Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers","date":"2023-05-21","arxiv_id":"2305.12567","n_code_links":1,"syntology":null},{"paper":null,"slug":"tcn-aa-a-wi-fi-based-temporal-convolution","title":"WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal","date":"2023-05-21","arxiv_id":"2305.18211","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-the-pre-trained-model-to-generate","slug":"teaching-the-pre-trained-model-to-generate","title":"Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification","date":"2023-05-21","arxiv_id":"2305.12463","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-fusion-transformers-for-streamflow","title":"Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence","date":"2023-05-21","arxiv_id":"2305.12335","n_code_links":0,"syntology":null},{"paper":"/paper/theoremqa-a-theorem-driven-question-answering","slug":"theoremqa-a-theorem-driven-question-answering","title":"TheoremQA: A Theorem-driven Question Answering dataset","date":"2023-05-21","arxiv_id":"2305.12524","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":8,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"10 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wenhuchen/theoremqa"],"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":["found_in_text","official"]}}},{"paper":null,"slug":"autoregressive-modeling-with-lookahead","title":"Autoregressive Modeling with Lookahead Attention","date":"2023-05-20","arxiv_id":"2305.12272","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-correctly-reason-over-contexts","title":"Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?","date":"2023-05-20","arxiv_id":"2305.12096","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdjur-br-a-golden-collection-of-legal","title":"CDJUR-BR -- A Golden Collection of Legal Document from Brazilian Justice with Fine-Grained Named Entities","date":"2023-05-20","arxiv_id":"2305.18315","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-deep-learning-models","title":"Comparative Analysis of Deep Learning Models for Brand Logo Classification in Real-World Scenarios","date":"2023-05-20","arxiv_id":"2305.12242","n_code_links":0,"syntology":null},{"paper":"/paper/contextualizing-argument-quality-assessment","slug":"contextualizing-argument-quality-assessment","title":"Contextualizing Argument Quality Assessment with Relevant Knowledge","date":"2023-05-20","arxiv_id":"2305.12280","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimental-results-from-applying-gpt-4-to","title":"Experimental results from applying GPT-4 to an unpublished formal language","date":"2023-05-20","arxiv_id":"2305.12196","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-to-compose-syntactic-and-semantic","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","date":"2023-05-20","arxiv_id":"2305.12169","n_code_links":0,"syntology":null},{"paper":"/paper/logicot-logical-chain-of-thought-instruction","slug":"logicot-logical-chain-of-thought-instruction","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","date":"2023-05-20","arxiv_id":"2305.12147","n_code_links":1,"syntology":null},{"paper":"/paper/make-transformer-great-again-for-time-series","slug":"make-transformer-great-again-for-time-series","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","date":"2023-05-20","arxiv_id":"2305.12095","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["wxie9/card"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"8279fbc7e8532a0f8edda7e7baab95c48397e4b8724950e2caab31a3daf27f9a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}