{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention-dropout/papers/54","list_of":"/method/attention-dropout","method":"Attention Dropout","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":54,"pages_in_order":109,"rows_per_page":100,"rows":[5301,5400],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention-dropout","prev":"/method/attention-dropout/papers/53","next":"/method/attention-dropout/papers/55","papers":[{"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/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":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/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/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":"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":"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/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":"/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":"/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/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":"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":"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/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":"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":null,"slug":"bi-vit-pushing-the-limit-of-vision","title":"Bi-ViT: Pushing the Limit of Vision Transformer Quantization","date":"2023-05-21","arxiv_id":"2305.12354","n_code_links":0,"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":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":"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/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":"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":"/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":null,"slug":"practical-pcg-through-large-language-models","title":"Practical PCG Through Large Language Models","date":"2023-05-20","arxiv_id":"2305.18243","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-the-architectures-like-pointer","slug":"revisiting-the-architectures-like-pointer","title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond","date":"2023-05-20","arxiv_id":"2305.12289","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentfin-1-0-entity-aware-sentiment-analysis","title":"SEntFiN 1.0: Entity-Aware Sentiment Analysis for Financial News","date":"2023-05-20","arxiv_id":"2305.12257","n_code_links":0,"syntology":null},{"paper":"/paper/what-makes-for-good-visual-tokenizers-for","slug":"what-makes-for-good-visual-tokenizers-for","title":"What Makes for Good Visual Tokenizers for Large Language Models?","date":"2023-05-20","arxiv_id":"2305.12223","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tencentarc/gvt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-sequence-to-sequence-approach-for-arabic","title":"A Sequence-to-Sequence Approach for Arabic Pronoun Resolution","date":"2023-05-19","arxiv_id":"2305.11529","n_code_links":0,"syntology":null},{"paper":null,"slug":"autotrial-prompting-language-models-for","title":"AutoTrial: Prompting Language Models for Clinical Trial Design","date":"2023-05-19","arxiv_id":"2305.11366","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-camel-an-open-source-expert-level","slug":"clinical-camel-an-open-source-expert-level","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","date":"2023-05-19","arxiv_id":"2305.12031","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bowang-lab/clinical-camel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-models-really-learn-to-follow-instructions","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","date":"2023-05-19","arxiv_id":"2305.11383","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-upper-limits-of-text-based","title":"Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights","date":"2023-05-19","arxiv_id":"2305.11700","n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-spatialnet-spatial-information-extraction","title":"Eye-SpatialNet: Spatial Information Extraction from Ophthalmology Notes","date":"2023-05-19","arxiv_id":"2305.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-foundation-models-privacy","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","date":"2023-05-19","arxiv_id":"2305.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-universal-phonetic-representation-in","title":"Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition","date":"2023-05-19","arxiv_id":"2305.11569","n_code_links":0,"syntology":null},{"paper":"/paper/pointgpt-auto-regressively-generative-pre-1","slug":"pointgpt-auto-regressively-generative-pre-1","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","date":"2023-05-19","arxiv_id":"2305.11487","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CGuangyan-BIT/PointGPT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-laws-for-language-encoding-models-in","slug":"scaling-laws-for-language-encoding-models-in","title":"Scaling laws for language encoding models in fMRI","date":"2023-05-19","arxiv_id":"2305.11863","n_code_links":1,"syntology":null},{"paper":"/paper/seegull-a-stereotype-benchmark-with-broad-geo","slug":"seegull-a-stereotype-benchmark-with-broad-geo","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","date":"2023-05-19","arxiv_id":"2305.11840","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-agreement-a-framework-for-fine-tuning","title":"Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions","date":"2023-05-19","arxiv_id":"2305.11460","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfzcot-a-self-prompt-zero-shot-cot-from","title":"Hint of Thought prompting: an explainable and zero-shot approach to reasoning tasks with LLMs","date":"2023-05-19","arxiv_id":"2305.11461","n_code_links":0,"syntology":null},{"paper":null,"slug":"ahead-of-time-p-tuning","title":"Ahead-of-Time P-Tuning","date":"2023-05-18","arxiv_id":"2305.10835","n_code_links":0,"syntology":null},{"paper":null,"slug":"aiwriting-relations-between-image-generation","title":"AIwriting: Relations Between Image Generation and Digital Writing","date":"2023-05-18","arxiv_id":"2305.10834","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-machines-and-children-using","title":"Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses","date":"2023-05-18","arxiv_id":"2305.11243","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-methods-for-extracting","title":"Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants","date":"2023-05-18","arxiv_id":"2305.10833","n_code_links":0,"syntology":null},{"paper":"/paper/ditto-a-simple-and-efficient-approach-to","slug":"ditto-a-simple-and-efficient-approach-to","title":"Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings","date":"2023-05-18","arxiv_id":"2305.10786","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-multiple-intent-conditioned-slot","title":"Generalized Multiple Intent Conditioned Slot Filling","date":"2023-05-18","arxiv_id":"2305.11023","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-planning-in-pddl-domains-with","slug":"generalized-planning-in-pddl-domains-with","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","date":"2023-05-18","arxiv_id":"2305.11014","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tomsilver/llm-genplan"],"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"]}}},{"paper":"/paper/large-language-models-can-be-guided-to-evade","slug":"large-language-models-can-be-guided-to-evade","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","date":"2023-05-18","arxiv_id":"2305.10847","n_code_links":1,"syntology":null},{"paper":"/paper/mlongt5-a-multilingual-and-efficient-text-to","slug":"mlongt5-a-multilingual-and-efficient-text-to","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","date":"2023-05-18","arxiv_id":"2305.11129","n_code_links":1,"syntology":null},{"paper":null,"slug":"pdp-parameter-free-differentiable-pruning-is","title":"PDP: Parameter-free Differentiable Pruning is All You Need","date":"2023-05-18","arxiv_id":"2305.11203","n_code_links":0,"syntology":null},{"paper":null,"slug":"trading-syntax-trees-for-wordpieces-target","title":"Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement","date":"2023-05-18","arxiv_id":"2305.11034","n_code_links":0,"syntology":null},{"paper":"/paper/a-quantitative-study-of-nlp-approaches-to","slug":"a-quantitative-study-of-nlp-approaches-to","title":"A quantitative study of NLP approaches to question difficulty estimation","date":"2023-05-17","arxiv_id":"2305.10236","n_code_links":1,"syntology":null},{"paper":"/paper/ad-kd-attribution-driven-knowledge","slug":"ad-kd-attribution-driven-knowledge","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","date":"2023-05-17","arxiv_id":"2305.10010","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 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":["brucewsy/ad-kd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/coedit-text-editing-by-task-specific","slug":"coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","n_code_links":1,"syntology":null},{"paper":"/paper/explaining-black-box-text-modules-in-natural","slug":"explaining-black-box-text-modules-in-natural","title":"Explaining black box text modules in natural language with language models","date":"2023-05-17","arxiv_id":"2305.09863","n_code_links":2,"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":["csinva/imodelsX","microsoft/automated-explanations"],"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":"from-chocolate-bunny-to-chocolate-crocodile","title":"From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?","date":"2023-05-17","arxiv_id":"2305.10568","n_code_links":0,"syntology":null},{"paper":"/paper/instruction-tuned-models-are-quick-learners","slug":"instruction-tuned-models-are-quick-learners","title":"Instruction Tuned Models are Quick Learners","date":"2023-05-17","arxiv_id":"2306.05539","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["srsawant34/efficient_instruction_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"interactive-learning-of-hierarchical-tasks","title":"Interactive Learning of Hierarchical Tasks from Dialog with GPT","date":"2023-05-17","arxiv_id":"2305.10349","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-completion-models-are-few","title":"Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs","date":"2023-05-17","arxiv_id":"2305.09858","n_code_links":0,"syntology":null},{"paper":"/paper/m3ke-a-massive-multi-level-multi-subject","slug":"m3ke-a-massive-multi-level-multi-subject","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","date":"2023-05-17","arxiv_id":"2305.10263","n_code_links":1,"syntology":null},{"paper":"/paper/smaller-language-models-are-better-black-box","slug":"smaller-language-models-are-better-black-box","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","date":"2023-05-17","arxiv_id":"2305.09859","n_code_links":1,"syntology":null},{"paper":"/paper/solving-cosine-similarity-underestimation","slug":"solving-cosine-similarity-underestimation","title":"Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting","date":"2023-05-17","arxiv_id":"2305.10610","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-gradient-descent-meets-derivative-free","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","date":"2023-05-17","arxiv_id":"2305.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-preliminary-analysis-on-the-code-generation","title":"A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions","date":"2023-05-16","arxiv_id":"2305.09402","n_code_links":0,"syntology":null},{"paper":"/paper/berttm-leveraging-contextualized-word","slug":"berttm-leveraging-contextualized-word","title":"CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling","date":"2023-05-16","arxiv_id":"2305.09329","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-stereotypes-using-entity-centric","slug":"measuring-stereotypes-using-entity-centric","title":"Measuring Dimensions of Self-Presentation in Twitter Bios and their Links to Misinformation Sharing","date":"2023-05-16","arxiv_id":"2305.09548","n_code_links":1,"syntology":null},{"paper":"/paper/weight-inherited-distillation-for-task","slug":"weight-inherited-distillation-for-task","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","date":"2023-05-16","arxiv_id":"2305.09098","n_code_links":1,"syntology":null},{"paper":"/paper/coreference-aware-double-channel-attention","slug":"coreference-aware-double-channel-attention","title":"Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension","date":"2023-05-15","arxiv_id":"2305.08348","n_code_links":1,"syntology":null},{"paper":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/keras-gpt-copilot-integrating-the-power-of","slug":"keras-gpt-copilot-integrating-the-power-of","title":"Keras GPT Copilot: Integrating the Power of Large Language Models in Deep Learning Model Development","date":"2023-05-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-rumination-for-pre-trained-language","slug":"knowledge-rumination-for-pre-trained-language","title":"Knowledge Rumination for Pre-trained Language Models","date":"2023-05-15","arxiv_id":"2305.08732","n_code_links":1,"syntology":null},{"paper":null,"slug":"private-training-set-inspection-in-mlaas","title":"Private Training Set Inspection in MLaaS","date":"2023-05-15","arxiv_id":"2305.09058","n_code_links":0,"syntology":null},{"paper":"/paper/rl4f-generating-natural-language-feedback","slug":"rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","arxiv_id":"2305.08844","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feyzaakyurek/rl4f"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/schema-adaptable-knowledge-graph-construction","slug":"schema-adaptable-knowledge-graph-construction","title":"Schema-adaptable Knowledge Graph Construction","date":"2023-05-15","arxiv_id":"2305.08703","n_code_links":1,"syntology":null},{"paper":null,"slug":"sensitivity-and-robustness-of-large-language","title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","date":"2023-05-15","arxiv_id":"2305.08714","n_code_links":0,"syntology":null},{"paper":"/paper/similarity-weighted-construction-of","slug":"similarity-weighted-construction-of","title":"Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks","date":"2023-05-15","arxiv_id":"2305.08495","n_code_links":1,"syntology":null},{"paper":"/paper/small-models-are-valuable-plug-ins-for-large","slug":"small-models-are-valuable-plug-ins-for-large","title":"Small Models are Valuable Plug-ins for Large Language Models","date":"2023-05-15","arxiv_id":"2305.08848","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["JetRunner/SuperICL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-classification-via-large-language-models","slug":"text-classification-via-large-language-models","title":"Text Classification via Large Language Models","date":"2023-05-15","arxiv_id":"2305.08377","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":["shannonai/gpt-cls-carp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text2gender-a-deep-learning-architecture-for","title":"Text2Gender: A Deep Learning Architecture for Analysis of Blogger's Age and Gender","date":"2023-05-15","arxiv_id":"2305.08633","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-llm-assisted-annotation-for-corpus","title":"Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology","date":"2023-05-15","arxiv_id":"2305.08339","n_code_links":0,"syntology":null},{"paper":"/paper/matsci-nlp-evaluating-scientific-language","slug":"matsci-nlp-evaluating-scientific-language","title":"MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling","date":"2023-05-14","arxiv_id":"2305.08264","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["banglab-udem-mila/nlp4matsci-acl23"],"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/mobile-env-a-universal-platform-for-training","slug":"mobile-env-a-universal-platform-for-training","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","date":"2023-05-14","arxiv_id":"2305.08144","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":11,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"11 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; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opendfm/mobile-env-expe","x-lance/mobile-env"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}}],"record_sha256":"45ace85f1bb2ec339b18d0139f98ac9b95ccb0fc506ed69c610196a6979cb058","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}