{"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/48","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":48,"pages_in_order":109,"rows_per_page":100,"rows":[4701,4800],"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/47","next":"/method/attention-dropout/papers/49","papers":[{"paper":null,"slug":"towards-improving-the-expressiveness-of","title":"Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information","date":"2023-08-31","arxiv_id":"2308.16836","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-compression-via-subspace","slug":"transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","arxiv_id":"2308.16475","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hyx1999/sp3"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"analyzing-character-and-consciousness-in-ai","title":"Analyzing Character and Consciousness in AI-Generated Social Content: A Case Study of Chirper, the AI Social Network","date":"2023-08-30","arxiv_id":"2309.08614","n_code_links":0,"syntology":null},{"paper":null,"slug":"jais-and-jais-chat-arabic-centric-foundation","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","date":"2023-08-30","arxiv_id":"2308.16149","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-data-preprocessors","title":"Large Language Models as Data Preprocessors","date":"2023-08-30","arxiv_id":"2308.16361","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-uncertainty-in-answers-from-any","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","date":"2023-08-30","arxiv_id":"2308.16175","n_code_links":0,"syntology":null},{"paper":"/paper/response-emergent-analogical-reasoning-in","slug":"response-emergent-analogical-reasoning-in","title":"Response: Emergent analogical reasoning in large language models","date":"2023-08-30","arxiv_id":"2308.16118","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-deepzen-speech-synthesis-system-for","title":"The DeepZen Speech Synthesis System for Blizzard Challenge 2023","date":"2023-08-30","arxiv_id":"2308.15945","n_code_links":0,"syntology":null},{"paper":null,"slug":"furchat-an-embodied-conversational-agent","title":"FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions","date":"2023-08-29","arxiv_id":"2308.15214","n_code_links":0,"syntology":null},{"paper":"/paper/multi-party-goal-tracking-with-llms-comparing","slug":"multi-party-goal-tracking-with-llms-comparing","title":"Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering","date":"2023-08-29","arxiv_id":"2308.15231","n_code_links":1,"syntology":null},{"paper":"/paper/spikebert-a-language-spikformer-trained-with","slug":"spikebert-a-language-spikformer-trained-with","title":"SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation","date":"2023-08-29","arxiv_id":"2308.15122","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Lvchangze/SpikeBERT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/aner-arabic-and-arabizi-named-entity","slug":"aner-arabic-and-arabizi-named-entity","title":"ANER: Arabic and Arabizi Named Entity Recognition using Transformer-Based Approach","date":"2023-08-28","arxiv_id":"2308.14669","n_code_links":1,"syntology":null},{"paper":null,"slug":"breaking-the-bank-with-chatgpt-few-shot-text","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","date":"2023-08-28","arxiv_id":"2308.14634","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-effects-in-large-language-models","slug":"cognitive-effects-in-large-language-models","title":"Cognitive Effects in Large Language Models","date":"2023-08-28","arxiv_id":"2308.14337","n_code_links":1,"syntology":null},{"paper":"/paper/distilled-gpt-for-source-code-summarization","slug":"distilled-gpt-for-source-code-summarization","title":"Distilled GPT for Source Code Summarization","date":"2023-08-28","arxiv_id":"2308.14731","n_code_links":1,"syntology":null},{"paper":"/paper/fire-food-image-to-recipe-generation","slug":"fire-food-image-to-recipe-generation","title":"FIRE: Food Image to REcipe generation","date":"2023-08-28","arxiv_id":"2308.14391","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":10,"n_instrument":2,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 2 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) · 4 unverified","official":{"repos":["prateekchhikara/fire"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"target-independent-xla-optimization-using","title":"Target-independent XLA optimization using Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14364","n_code_links":0,"syntology":null},{"paper":"/paper/textrolspeech-a-text-style-control-speech","slug":"textrolspeech-a-text-style-control-speech","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","date":"2023-08-28","arxiv_id":"2308.14430","n_code_links":1,"syntology":null},{"paper":"/paper/ummaformer-a-universal-multimodal-adaptive-1","slug":"ummaformer-a-universal-multimodal-adaptive-1","title":"UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization","date":"2023-08-28","arxiv_id":"2308.14395","n_code_links":1,"syntology":null},{"paper":"/paper/unipt-universal-parallel-tuning-for-transfer","slug":"unipt-universal-parallel-tuning-for-transfer","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","date":"2023-08-28","arxiv_id":"2308.14316","n_code_links":1,"syntology":null},{"paper":"/paper/examining-user-friendly-and-open-sourced","slug":"examining-user-friendly-and-open-sourced","title":"Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models","date":"2023-08-27","arxiv_id":"2308.14149","n_code_links":1,"syntology":null},{"paper":"/paper/a-wide-evaluation-of-chatgpt-on-affective","slug":"a-wide-evaluation-of-chatgpt-on-affective","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","date":"2023-08-26","arxiv_id":"2308.13911","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","n_code_links":0,"syntology":null},{"paper":"/paper/cultural-alignment-in-large-language-models","slug":"cultural-alignment-in-large-language-models","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","date":"2023-08-25","arxiv_id":"2309.12342","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-knowledge-and-reinforcement","title":"Leveraging Knowledge and Reinforcement Learning for Enhanced Reliability of Language Models","date":"2023-08-25","arxiv_id":"2308.13467","n_code_links":0,"syntology":null},{"paper":"/paper/mllm-dataengine-an-iterative-refinement","slug":"mllm-dataengine-an-iterative-refinement","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","date":"2023-08-25","arxiv_id":"2308.13566","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opendatalab/mllm-dataengine"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transforming-the-output-of-generative-pre","title":"Transforming the Output of Generative Pre-trained Transformer: The Influence of the PGI Framework on Attention Dynamics","date":"2023-08-25","arxiv_id":"2308.13317","n_code_links":0,"syntology":null},{"paper":"/paper/a-small-and-fast-bert-for-chinese-medical","slug":"a-small-and-fast-bert-for-chinese-medical","title":"A Small and Fast BERT for Chinese Medical Punctuation Restoration","date":"2023-08-24","arxiv_id":"2308.12568","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-hungarian-text-processing-with","slug":"advancing-hungarian-text-processing-with","title":"Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines","date":"2023-08-24","arxiv_id":"2308.12635","n_code_links":2,"syntology":null},{"paper":null,"slug":"financial-news-analytics-using-fine-tuned","title":"Financial News Analytics Using Fine-Tuned Llama 2 GPT Model","date":"2023-08-24","arxiv_id":"2308.13032","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-bert-for-embeddings-for-recommendation","title":"Multi-BERT for Embeddings for Recommendation System","date":"2023-08-24","arxiv_id":"2308.13050","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-embedding-models-for-ancient-greek","slug":"sentence-embedding-models-for-ancient-greek","title":"Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation","date":"2023-08-24","arxiv_id":"2308.13116","n_code_links":2,"syntology":null},{"paper":null,"slug":"text-similarity-from-image-contents-using","title":"Text Similarity from Image Contents using Statistical and Semantic Analysis Techniques","date":"2023-08-24","arxiv_id":"2308.12842","n_code_links":0,"syntology":null},{"paper":null,"slug":"simple-is-better-and-large-is-not-enough","title":"Simple is Better and Large is Not Enough: Towards Ensembling of Foundational Language Models","date":"2023-08-23","arxiv_id":"2308.12272","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-on-graphs","slug":"evaluating-large-language-models-on-graphs","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","date":"2023-08-22","arxiv_id":"2308.11224","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["ayame1006/llmtograph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-effectiveness-of-gpt-models-in","title":"Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test","date":"2023-08-22","arxiv_id":"2308.11827","n_code_links":0,"syntology":null},{"paper":"/paper/mulmarker-a-gpt-assisted-comprehensive","slug":"mulmarker-a-gpt-assisted-comprehensive","title":"MulMarker: a comprehensive framework for identifying multi-gene prognostic signatures","date":"2023-08-22","arxiv_id":"2308.11349","n_code_links":1,"syntology":null},{"paper":null,"slug":"tryage-real-time-intelligent-routing-of-user","title":"Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models","date":"2023-08-22","arxiv_id":"2308.11601","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-in-the-loop-adaptive-decision-making-for","title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","date":"2023-08-21","arxiv_id":"2308.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradientcoin-a-peer-to-peer-decentralized","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","date":"2023-08-21","arxiv_id":"2308.10502","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-as-a-user-simulator","slug":"large-language-model-as-a-user-simulator","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","date":"2023-08-21","arxiv_id":"2308.11534","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"0 ran · 2 unverified","official":null}},{"paper":"/paper/large-language-models-on-wikipedia-style","slug":"large-language-models-on-wikipedia-style","title":"Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts","date":"2023-08-21","arxiv_id":"2308.10410","n_code_links":1,"syntology":null},{"paper":"/paper/spikingbert-distilling-bert-to-train-spiking","slug":"spikingbert-distilling-bert-to-train-spiking","title":"SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation","date":"2023-08-21","arxiv_id":"2308.10873","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":8,"n_instrument":5,"unverified":4,"pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["neurocomplab-psu/spikingbert"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/activation-addition-steering-language-models","slug":"activation-addition-steering-language-models","title":"Steering Language Models With Activation Engineering","date":"2023-08-20","arxiv_id":"2308.10248","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["montemac/activation_additions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-good-are-large-language-models-at-out-of","slug":"how-good-are-large-language-models-at-out-of","title":"How Good Are LLMs at Out-of-Distribution Detection?","date":"2023-08-20","arxiv_id":"2308.10261","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["awenbocc/llm-ood"],"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/improving-adversarial-robustness-of-masked","slug":"improving-adversarial-robustness-of-masked","title":"Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting","date":"2023-08-20","arxiv_id":"2308.10315","n_code_links":1,"syntology":null},{"paper":"/paper/data-to-text-generation-for-severely-under","slug":"data-to-text-generation-for-severely-under","title":"Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate","date":"2023-08-19","arxiv_id":"2308.09957","n_code_links":1,"syntology":null},{"paper":null,"slug":"east-efficient-and-accurate-secure","title":"East: Efficient and Accurate Secure Transformer Framework for Inference","date":"2023-08-19","arxiv_id":"2308.09923","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-closed-or-small-language-models-for-text","title":"Open, Closed, or Small Language Models for Text Classification?","date":"2023-08-19","arxiv_id":"2308.10092","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-multi-class-text-classification-a","title":"Optimizing Multi-Class Text Classification: A Diverse Stacking Ensemble Framework Utilizing Transformers","date":"2023-08-19","arxiv_id":"2308.11519","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-tailored-handwritten-text-recognition","title":"A tailored Handwritten-Text-Recognition System for Medieval Latin","date":"2023-08-18","arxiv_id":"2308.09368","n_code_links":0,"syntology":null},{"paper":"/paper/how-susceptible-are-llms-to-logical-fallacies","slug":"how-susceptible-are-llms-to-logical-fallacies","title":"How susceptible are LLMs to Logical Fallacies?","date":"2023-08-18","arxiv_id":"2308.09853","n_code_links":1,"syntology":null},{"paper":"/paper/learning-representations-on-logs-for-aiops","slug":"learning-representations-on-logs-for-aiops","title":"Learning Representations on Logs for AIOps","date":"2023-08-18","arxiv_id":"2308.11526","n_code_links":1,"syntology":null},{"paper":"/paper/predictive-authoring-for-brazilian-portuguese","slug":"predictive-authoring-for-brazilian-portuguese","title":"Predictive Authoring for Brazilian Portuguese Augmentative and Alternative Communication","date":"2023-08-18","arxiv_id":"2308.09497","n_code_links":1,"syntology":null},{"paper":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":16,"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) · 6 unverified","official":null}},{"paper":"/paper/a-comparative-study-of-text-embedding-models","slug":"a-comparative-study-of-text-embedding-models","title":"A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug Reports","date":"2023-08-17","arxiv_id":"2308.09193","n_code_links":1,"syntology":null},{"paper":"/paper/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluation-of-really-good-grammatical-error","slug":"evaluation-of-really-good-grammatical-error","title":"Evaluation of really good grammatical error correction","date":"2023-08-17","arxiv_id":"2308.08982","n_code_links":1,"syntology":null},{"paper":null,"slug":"mascqa-a-question-answering-dataset-for","title":"MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models","date":"2023-08-17","arxiv_id":"2308.09115","n_code_links":0,"syntology":null},{"paper":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wyl-willing/MindMap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-preliminary-study-on-a-conceptual-game","title":"A Preliminary Study on a Conceptual Game Feature Generation and Recommendation System","date":"2023-08-16","arxiv_id":"2308.13538","n_code_links":0,"syntology":null},{"paper":"/paper/bioptimus-pre-training-an-optimal-biomedical","slug":"bioptimus-pre-training-an-optimal-biomedical","title":"BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition","date":"2023-08-16","arxiv_id":"2308.08625","n_code_links":1,"syntology":null},{"paper":null,"slug":"mitigating-the-exposure-bias-in-sentence","title":"Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction","date":"2023-08-16","arxiv_id":"2308.08442","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-deception-reverse-penetrating-the","title":"Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models","date":"2023-08-16","arxiv_id":"2308.11521","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-test-case-generation-using-code","title":"Domain Adaptation for Code Model-based Unit Test Case Generation","date":"2023-08-15","arxiv_id":"2308.08033","n_code_links":0,"syntology":null},{"paper":null,"slug":"backward-reasoning-in-large-language-models","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","date":"2023-08-15","arxiv_id":"2308.07758","n_code_links":0,"syntology":null},{"paper":null,"slug":"beware-of-deception-detecting-half-truth-and","title":"\"Beware of deception\": Detecting Half-Truth and Debunking it through Controlled Claim Editing","date":"2023-08-15","arxiv_id":"2308.07973","n_code_links":0,"syntology":null},{"paper":null,"slug":"calypso-llms-as-dungeon-masters-assistants","title":"CALYPSO: LLMs as Dungeon Masters' Assistants","date":"2023-08-15","arxiv_id":"2308.07540","n_code_links":0,"syntology":null},{"paper":null,"slug":"ds4dh-at-smm4h-2023-zero-shot-adverse-drug","title":"DS4DH at #SMM4H 2023: Zero-Shot Adverse Drug Events Normalization using Sentence Transformers and Reciprocal-Rank Fusion","date":"2023-08-15","arxiv_id":"2308.12877","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-stakeholder-material-information-from","title":"Finding Stakeholder-Material Information from 10-K Reports using Fine-Tuned BERT and LSTM Models","date":"2023-08-15","arxiv_id":"2308.07522","n_code_links":0,"syntology":null},{"paper":"/paper/from-commit-message-generation-to-history","slug":"from-commit-message-generation-to-history","title":"From Commit Message Generation to History-Aware Commit Message Completion","date":"2023-08-15","arxiv_id":"2308.07655","n_code_links":1,"syntology":null},{"paper":null,"slug":"multischubert-effective-multimodal-fusion-for","title":"MultiSChuBERT: Effective Multimodal Fusion for Scholarly Document Quality Prediction","date":"2023-08-15","arxiv_id":"2308.07971","n_code_links":0,"syntology":null},{"paper":null,"slug":"spm-structured-pretraining-and-matching","title":"SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search","date":"2023-08-15","arxiv_id":"2308.07711","n_code_links":0,"syntology":null},{"paper":"/paper/synthesizing-political-zero-shot-relation","slug":"synthesizing-political-zero-shot-relation","title":"Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification","date":"2023-08-15","arxiv_id":"2308.07876","n_code_links":1,"syntology":null},{"paper":"/paper/ternary-singular-value-decomposition-as-a","slug":"ternary-singular-value-decomposition-as-a","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","date":"2023-08-15","arxiv_id":"2308.07641","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ozzzp/ternary_decompose"],"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":null,"slug":"approximating-human-like-few-shot-learning","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","date":"2023-08-14","arxiv_id":"2308.06942","n_code_links":0,"syntology":null},{"paper":"/paper/easyedit-an-easy-to-use-knowledge-editing","slug":"easyedit-an-easy-to-use-knowledge-editing","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","date":"2023-08-14","arxiv_id":"2308.07269","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zjunlp/easyedit","zjunlp/knowlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-individual-trajectories-using-gpt","title":"Generating Individual Trajectories Using GPT-2 Trained from Scratch on Encoded Spatiotemporal Data","date":"2023-08-14","arxiv_id":"2308.07940","n_code_links":0,"syntology":null},{"paper":"/paper/llm-self-defense-by-self-examination-llms","slug":"llm-self-defense-by-self-examination-llms","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","date":"2023-08-14","arxiv_id":"2308.07308","n_code_links":1,"syntology":null},{"paper":null,"slug":"playing-with-words-comparing-the-vocabulary","title":"Playing with Words: Comparing the Vocabulary and Lexical Richness of ChatGPT and Humans","date":"2023-08-14","arxiv_id":"2308.07462","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-similarity-loss-for-neural-source","slug":"semantic-similarity-loss-for-neural-source","title":"Semantic Similarity Loss for Neural Source Code Summarization","date":"2023-08-14","arxiv_id":"2308.07429","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-ensemble-approach-to-question","title":"An Ensemble Approach to Question Classification: Integrating Electra Transformer, GloVe, and LSTM","date":"2023-08-13","arxiv_id":"2308.06828","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-face-recognition-from-caption","title":"Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation","date":"2023-08-13","arxiv_id":"2308.06866","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-student-errors-in-experimentation","title":"Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters","date":"2023-08-11","arxiv_id":"2308.06088","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-phenotype-recognition-in-clinical","slug":"enhancing-phenotype-recognition-in-clinical","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","date":"2023-08-11","arxiv_id":"2308.06294","n_code_links":1,"syntology":null},{"paper":"/paper/identification-of-the-relevance-of-comments","slug":"identification-of-the-relevance-of-comments","title":"Identification of the Relevance of Comments in Codes Using Bag of Words and Transformer Based Models","date":"2023-08-11","arxiv_id":"2308.06144","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-in-cryptocurrency","title":"Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?","date":"2023-08-11","arxiv_id":"2308.06032","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-to-identify-social","slug":"large-language-models-to-identify-social","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","date":"2023-08-11","arxiv_id":"2308.06354","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["aim-harvard/sdoh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"task-conditioned-bert-for-joint-intent","title":"Task Conditioned BERT for Joint Intent Detection and Slot-filling","date":"2023-08-11","arxiv_id":"2308.06165","n_code_links":0,"syntology":null},{"paper":null,"slug":"thinking-like-an-expert-multimodal-hypergraph","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","date":"2023-08-11","arxiv_id":"2308.06207","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-low-rank-adaptation-of-segment","slug":"adaptive-low-rank-adaptation-of-segment","title":"Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection","date":"2023-08-10","arxiv_id":"2308.05426","n_code_links":1,"syntology":null},{"paper":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","n_code_links":2,"syntology":{"ran":16,"of":27,"n_ran_checked":16,"n_instrument":0,"unverified":11,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"bringing-order-into-the-realm-of-transformer","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","date":"2023-08-10","arxiv_id":"2308.05502","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-machine-learning-and-transformer","title":"Exploring Machine Learning and Transformer-based Approaches for Deceptive Text Classification: A Comparative Analysis","date":"2023-08-10","arxiv_id":"2308.05476","n_code_links":0,"syntology":null},{"paper":"/paper/metacognitive-prompting-improves","slug":"metacognitive-prompting-improves","title":"Metacognitive Prompting Improves Understanding in Large Language Models","date":"2023-08-10","arxiv_id":"2308.05342","n_code_links":1,"syntology":null},{"paper":"/paper/rtllm-an-open-source-benchmark-for-design-rtl","slug":"rtllm-an-open-source-benchmark-for-design-rtl","title":"RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model","date":"2023-08-10","arxiv_id":"2308.05345","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":["hkust-zhiyao/rtllm"],"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":"testing-gpt-4-with-wolfram-alpha-and-code","title":"Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems","date":"2023-08-10","arxiv_id":"2308.05713","n_code_links":0,"syntology":null},{"paper":"/paper/weaverbird-empowering-financial-decision","slug":"weaverbird-empowering-financial-decision","title":"WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine","date":"2023-08-10","arxiv_id":"2308.05361","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-prompt-once-on-the-capabilities-of","slug":"you-only-prompt-once-on-the-capabilities-of","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","date":"2023-08-10","arxiv_id":"2308.05596","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 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":["xinleihe/toxic-prompt"],"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":"an-empirical-study-on-using-large-language-1","title":"An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures","date":"2023-08-09","arxiv_id":"2308.04898","n_code_links":0,"syntology":null}],"record_sha256":"82e5f22ecde443ef59402c538caed9a37d023ba1a9c1eb1ee4bb4c0e575f0d6e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}