{"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/56","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":56,"pages_in_order":109,"rows_per_page":100,"rows":[5501,5600],"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/55","next":"/method/attention-dropout/papers/57","papers":[{"paper":null,"slug":"neural-keyphrase-generation-analysis-and-1","title":"Neural Keyphrase Generation: Analysis and Evaluation","date":"2023-04-27","arxiv_id":"2304.13883","n_code_links":0,"syntology":null},{"paper":null,"slug":"origin-tracing-and-detecting-of-llms","title":"Origin Tracing and Detecting of LLMs","date":"2023-04-27","arxiv_id":"2304.14072","n_code_links":0,"syntology":null},{"paper":"/paper/pybibx-a-python-library-for-bibliometric-and","slug":"pybibx-a-python-library-for-bibliometric-and","title":"pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools","date":"2023-04-27","arxiv_id":"2304.14516","n_code_links":1,"syntology":null},{"paper":"/paper/swectrl-mini-a-data-transparent-transformer","slug":"swectrl-mini-a-data-transparent-transformer","title":"SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish","date":"2023-04-27","arxiv_id":"2304.13994","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-based-reasoning-framework-for-adaptive","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","date":"2023-04-26","arxiv_id":"2304.13301","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-5-and-gpt-4-for","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","date":"2023-04-26","arxiv_id":"2304.13714","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-curious-case-of-code-prompts","slug":"exploring-the-curious-case-of-code-prompts","title":"Exploring the Curious Case of Code Prompts","date":"2023-04-26","arxiv_id":"2304.13250","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["zharry29/codex_vs_gpt3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"extracting-structured-seed-mediated-gold","title":"Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3","date":"2023-04-26","arxiv_id":"2304.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-with-abnormal-examples","title":"Fine Tuning with Abnormal Examples","date":"2023-04-26","arxiv_id":"2304.13783","n_code_links":0,"syntology":null},{"paper":"/paper/hausanlp-at-semeval-2023-task-12-leveraging","slug":"hausanlp-at-semeval-2023-task-12-leveraging","title":"HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis","date":"2023-04-26","arxiv_id":"2304.13634","n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-multi-modal-dbmss-for-seamless","title":"Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables","date":"2023-04-26","arxiv_id":"2304.13559","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-mbib-the-first-media-bias","slug":"introducing-mbib-the-first-media-bias","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","date":"2023-04-25","arxiv_id":"2304.13148","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-massive-multitask-chinese","slug":"measuring-massive-multitask-chinese","title":"Measuring Massive Multitask Chinese Understanding","date":"2023-04-25","arxiv_id":"2304.12986","n_code_links":2,"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":["Felixgithub2017/MMCU"],"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","unlocated"]}}},{"paper":null,"slug":"nlp-ltu-at-semeval-2023-task-10-the-impact-of","title":"NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset","date":"2023-04-25","arxiv_id":"2304.12847","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-compression-with-large-language","title":"Semantic Compression With Large Language Models","date":"2023-04-25","arxiv_id":"2304.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-potential-of-visual-chatgpt-for-remote","title":"The Potential of Visual ChatGPT For Remote Sensing","date":"2023-04-25","arxiv_id":"2304.13009","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-about-prosody","title":"What does BERT learn about prosody?","date":"2023-04-25","arxiv_id":"2304.12706","n_code_links":0,"syntology":null},{"paper":"/paper/generation-driven-contrastive-self-training","slug":"generation-driven-contrastive-self-training","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","date":"2023-04-24","arxiv_id":"2304.11872","n_code_links":1,"syntology":null},{"paper":"/paper/paragraph2graph-a-gnn-based-framework-for","slug":"paragraph2graph-a-gnn-based-framework-for","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","date":"2023-04-24","arxiv_id":"2304.11810","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-embeddings-for-entity-resolution","slug":"pre-trained-embeddings-for-entity-resolution","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","date":"2023-04-24","arxiv_id":"2304.12329","n_code_links":1,"syntology":null},{"paper":"/paper/socialdial-a-benchmark-for-socially-aware","slug":"socialdial-a-benchmark-for-socially-aware","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","date":"2023-04-24","arxiv_id":"2304.12026","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-challenges-of-deploying-bert-based","slug":"exploring-challenges-of-deploying-bert-based","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","date":"2023-04-23","arxiv_id":"2304.11520","n_code_links":2,"syntology":null},{"paper":"/paper/boosting-theory-of-mind-performance-in-large","slug":"boosting-theory-of-mind-performance-in-large","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","date":"2023-04-22","arxiv_id":"2304.11490","n_code_links":1,"syntology":null},{"paper":null,"slug":"l3cube-indicsbert-a-simple-approach-for","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","date":"2023-04-22","arxiv_id":"2304.11434","n_code_links":0,"syntology":null},{"paper":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-clinical-knowledge-extraction-for","title":"BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis","date":"2023-04-21","arxiv_id":"2304.10996","n_code_links":0,"syntology":null},{"paper":"/paper/building-multimodal-ai-chatbots","slug":"building-multimodal-ai-chatbots","title":"Building Multimodal AI Chatbots","date":"2023-04-21","arxiv_id":"2305.03512","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-transformer-language-models-on-1","slug":"evaluating-transformer-language-models-on-1","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","date":"2023-04-21","arxiv_id":"2304.10977","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-anxiety-in-large-language-models","title":"Inducing anxiety in large language models can induce bias","date":"2023-04-21","arxiv_id":"2304.11111","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-deep-learning-for-credit-rating","slug":"multi-modal-deep-learning-for-credit-rating","title":"Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams","date":"2023-04-21","arxiv_id":"2304.10740","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2time-transformer-based-article-time","title":"Text2Time: Transformer-based Article Time Period Prediction","date":"2023-04-21","arxiv_id":"2304.10859","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dark-side-of-chatgpt-legal-and-ethical","title":"The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination","date":"2023-04-21","arxiv_id":"2304.14347","n_code_links":0,"syntology":null},{"paper":null,"slug":"who-s-the-best-detective-llms-vs-mls-in","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","date":"2023-04-21","arxiv_id":"2304.11257","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-specific-continued-pretraining-of","title":"Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health","date":"2023-04-20","arxiv_id":"2304.10447","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-cross-modal-information-retrieval-possible","title":"Is Cross-modal Information Retrieval Possible without Training?","date":"2023-04-20","arxiv_id":"2304.11095","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-semantics-towards-better-natural","title":"Meta Semantics: Towards better natural language understanding and reasoning","date":"2023-04-20","arxiv_id":"2304.10663","n_code_links":0,"syntology":null},{"paper":null,"slug":"movie-box-office-prediction-with-self","title":"Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining","date":"2023-04-20","arxiv_id":"2304.10311","n_code_links":0,"syntology":null},{"paper":"/paper/safety-assessment-of-chinese-large-language","slug":"safety-assessment-of-chinese-large-language","title":"Safety Assessment of Chinese Large Language Models","date":"2023-04-20","arxiv_id":"2304.10436","n_code_links":2,"syntology":null},{"paper":null,"slug":"sinc-spatial-composition-of-3d-human-motions","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","date":"2023-04-20","arxiv_id":"2304.10417","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-sense-induction-with-knowledge-1","title":"Word Sense Induction with Knowledge Distillation from BERT","date":"2023-04-20","arxiv_id":"2304.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"catch-me-if-you-can-identifying-fraudulent","title":"Catch Me If You Can: Identifying Fraudulent Physician Reviews with Large Language Models Using Generative Pre-Trained Transformers","date":"2023-04-19","arxiv_id":"2304.09948","n_code_links":0,"syntology":null},{"paper":"/paper/genegpt-teaching-large-language-models-to-use","slug":"genegpt-teaching-large-language-models-to-use","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","date":"2023-04-19","arxiv_id":"2304.09667","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ncbi/GeneGPT"],"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":"how-to-do-things-with-deep-learning-code","title":"How to Do Things with Deep Learning Code","date":"2023-04-19","arxiv_id":"2304.09406","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-transformer-to-1m-tokens-and-beyond","slug":"scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","date":"2023-04-19","arxiv_id":"2304.11062","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["booydar/t5-experiments"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"supporting-human-ai-collaboration-in-auditing","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","date":"2023-04-19","arxiv_id":"2304.09991","n_code_links":0,"syntology":null},{"paper":"/paper/surgicalgpt-end-to-end-language-vision-gpt","slug":"surgicalgpt-end-to-end-language-vision-gpt","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","date":"2023-04-19","arxiv_id":"2304.09974","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lalithjets/surgicalgpt"],"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":"/paper/tiefake-title-text-similarity-and-emotion","slug":"tiefake-title-text-similarity-and-emotion","title":"TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection","date":"2023-04-19","arxiv_id":"2304.09421","n_code_links":2,"syntology":null},{"paper":null,"slug":"bim-gpt-a-prompt-based-virtual-assistant","title":"BIM-GPT: a Prompt-Based Virtual Assistant Framework for BIM Information Retrieval","date":"2023-04-18","arxiv_id":"2304.09333","n_code_links":0,"syntology":null},{"paper":null,"slug":"cancergpt-few-shot-drug-pair-synergy","title":"CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models","date":"2023-04-18","arxiv_id":"2304.10946","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-interaction-for-content-generation","title":"LLM-based Interaction for Content Generation: A Case Study on the Perception of Employees in an IT department","date":"2023-04-18","arxiv_id":"2304.09064","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-suppression-accurate-quantization-of","slug":"outlier-suppression-accurate-quantization-of","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","date":"2023-04-18","arxiv_id":"2304.09145","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["modeltc/outlier_suppression_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-empirical-study-of-multitask-learning-to","slug":"an-empirical-study-of-multitask-learning-to","title":"An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems","date":"2023-04-17","arxiv_id":"2304.08115","n_code_links":1,"syntology":null},{"paper":"/paper/context-dependent-embedding-utterance","slug":"context-dependent-embedding-utterance","title":"Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations","date":"2023-04-17","arxiv_id":"2304.08216","n_code_links":1,"syntology":null},{"paper":"/paper/from-zero-to-hero-examining-the-power-of","slug":"from-zero-to-hero-examining-the-power-of","title":"From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.07995","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":["sail-sg/symbolic-instruction-tuning"],"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":"/paper/instructuie-multi-task-instruction-tuning-for","slug":"instructuie-multi-task-instruction-tuning-for","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","date":"2023-04-17","arxiv_id":"2304.08085","n_code_links":1,"syntology":null},{"paper":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","n_code_links":2,"syntology":null},{"paper":null,"slug":"multimodal-short-video-rumor-detection-system","title":"Multimodal Short Video Rumor Detection System Based on Contrastive Learning","date":"2023-04-17","arxiv_id":"2304.08401","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-product-development-npd-through-social","title":"New Product Development (NPD) through Social Media-based Analysis by Comparing Word2Vec and BERT Word Embeddings","date":"2023-04-17","arxiv_id":"2304.08369","n_code_links":0,"syntology":null},{"paper":null,"slug":"supporting-qualitative-analysis-with-large","title":"Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding","date":"2023-04-17","arxiv_id":"2304.10548","n_code_links":0,"syntology":null},{"paper":"/paper/the-minipile-challenge-for-data-efficient","slug":"the-minipile-challenge-for-data-efficient","title":"The MiniPile Challenge for Data-Efficient Language Models","date":"2023-04-17","arxiv_id":"2304.08442","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-virtual-simulation-pilot-agent-for-training","title":"A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers","date":"2023-04-16","arxiv_id":"2304.07842","n_code_links":0,"syntology":null},{"paper":"/paper/argugpt-evaluating-understanding-and","slug":"argugpt-evaluating-understanding-and","title":"ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models","date":"2023-04-16","arxiv_id":"2304.07666","n_code_links":2,"syntology":null},{"paper":null,"slug":"automated-program-repair-based-on-code-review","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","date":"2023-04-16","arxiv_id":"2304.07840","n_code_links":0,"syntology":null},{"paper":null,"slug":"sabia-portuguese-large-language-models","title":"Sabiá: Portuguese Large Language Models","date":"2023-04-16","arxiv_id":"2304.07880","n_code_links":0,"syntology":null},{"paper":"/paper/sikugpt-a-generative-pre-trained-model-for","slug":"sikugpt-a-generative-pre-trained-model-for","title":"SikuGPT: A Generative Pre-trained Model for Intelligent Information Processing of Ancient Texts from the Perspective of Digital Humanities","date":"2023-04-16","arxiv_id":"2304.07778","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-instruction-following-language","slug":"towards-better-instruction-following-language","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","date":"2023-04-16","arxiv_id":"2304.07854","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-chatgpt-forecast-stock-price-movements","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","date":"2023-04-15","arxiv_id":"2304.07619","n_code_links":0,"syntology":null},{"paper":"/paper/api-bank-a-benchmark-for-tool-augmented-llms","slug":"api-bank-a-benchmark-for-tool-augmented-llms","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","date":"2023-04-14","arxiv_id":"2304.08244","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"chatgpt-applications-opportunities-and","title":"ChatGPT: Applications, Opportunities, and Threats","date":"2023-04-14","arxiv_id":"2304.09103","n_code_links":0,"syntology":null},{"paper":"/paper/medalpaca-an-open-source-collection-of","slug":"medalpaca-an-open-source-collection-of","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","date":"2023-04-14","arxiv_id":"2304.08247","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/simplex-a-lexical-text-simplification","slug":"simplex-a-lexical-text-simplification","title":"SimpLex: a lexical text simplification architecture","date":"2023-04-14","arxiv_id":"2304.07002","n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-code-generation","title":"Stochastic Code Generation","date":"2023-04-14","arxiv_id":"2304.08243","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-mapping-of-cve-vulnerability","title":"Automated Mapping of CVE Vulnerability Records to MITRE CWE Weaknesses","date":"2023-04-13","arxiv_id":"2304.11130","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-cites-the-most-cited-articles-and","title":"ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts. As a result, AI may amplify the Matthew Effect in environmental science","date":"2023-04-13","arxiv_id":"2304.06794","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-social-biases-in-recent-large","title":"Evaluation of Social Biases in Recent Large Pre-Trained Models","date":"2023-04-13","arxiv_id":"2304.06861","n_code_links":0,"syntology":null},{"paper":"/paper/pgtask-introducing-the-task-of-profile","slug":"pgtask-introducing-the-task-of-profile","title":"PGTask: Introducing the Task of Profile Generation from Dialogues","date":"2023-04-13","arxiv_id":"2304.06634","n_code_links":1,"syntology":null},{"paper":"/paper/shall-we-pretrain-autoregressive-language","slug":"shall-we-pretrain-autoregressive-language","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","date":"2023-04-13","arxiv_id":"2304.06762","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-does-clip-know-about-a-red-circle-visual","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","date":"2023-04-13","arxiv_id":"2304.06712","n_code_links":0,"syntology":null},{"paper":"/paper/detection-of-fake-generated-scientific","slug":"detection-of-fake-generated-scientific","title":"Detection of Fake Generated Scientific Abstracts","date":"2023-04-12","arxiv_id":"2304.06148","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-chatgpt-model-for-vulnerability","title":"Evaluation of ChatGPT Model for Vulnerability Detection","date":"2023-04-12","arxiv_id":"2304.07232","n_code_links":0,"syntology":null},{"paper":"/paper/localizing-model-behavior-with-path-patching","slug":"localizing-model-behavior-with-path-patching","title":"Localizing Model Behavior with Path Patching","date":"2023-04-12","arxiv_id":"2304.05969","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["redwoodresearch/rust_circuit_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"approximating-human-evaluation-of-social","title":"Approximating Online Human Evaluation of Social Chatbots with Prompting","date":"2023-04-11","arxiv_id":"2304.05253","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-optimization-of-catalysts-with-in","slug":"bayesian-optimization-of-catalysts-with-in","title":"Bayesian Optimization of Catalysis With In-Context Learning","date":"2023-04-11","arxiv_id":"2304.05341","n_code_links":2,"syntology":null},{"paper":null,"slug":"distinguishing-chatgpt-3-5-4-generated-and","title":"Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis","date":"2023-04-11","arxiv_id":"2304.05534","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-foundation-models-for","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","date":"2023-04-11","arxiv_id":"2304.05336","n_code_links":0,"syntology":null},{"paper":"/paper/multi-step-jailbreaking-privacy-attacks-on","slug":"multi-step-jailbreaking-privacy-attacks-on","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","date":"2023-04-11","arxiv_id":"2304.05197","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkust-knowcomp/llm-multistep-jailbreak"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-preserving-word-order-importance","slug":"towards-preserving-word-order-importance","title":"Towards preserving word order importance through Forced Invalidation","date":"2023-04-11","arxiv_id":"2304.05221","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-large-language-models-efficiently","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","date":"2023-04-11","arxiv_id":"2304.05511","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-reading-passage-generation-with","title":"Automated Reading Passage Generation with OpenAI's Large Language Model","date":"2023-04-10","arxiv_id":"2304.04616","n_code_links":0,"syntology":null},{"paper":null,"slug":"incorporating-structured-sentences-with-time","title":"Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction","date":"2023-04-10","arxiv_id":"2304.04717","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-good-sentiment-analyzer-a","slug":"is-chatgpt-a-good-sentiment-analyzer-a","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","date":"2023-04-10","arxiv_id":"2304.04339","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["nustm/chatgpt-sentiment-evaluation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"on-the-possibilities-of-ai-generated-text","title":"On the Possibilities of AI-Generated Text Detection","date":"2023-04-10","arxiv_id":"2304.04736","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-ready-for","slug":"are-large-language-models-ready-for","title":"Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding","date":"2023-04-09","arxiv_id":"2304.05368","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-tokenize-for-generative-retrieval","slug":"learning-to-tokenize-for-generative-retrieval","title":"Learning to Tokenize for Generative Retrieval","date":"2023-04-09","arxiv_id":"2304.04171","n_code_links":1,"syntology":null},{"paper":"/paper/factify-2-a-multimodal-fake-news-and-satire","slug":"factify-2-a-multimodal-fake-news-and-satire","title":"Factify 2: A Multimodal Fake News and Satire News Dataset","date":"2023-04-08","arxiv_id":"2304.03897","n_code_links":1,"syntology":null},{"paper":null,"slug":"flexmoe-scaling-large-scale-sparse-pre","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","date":"2023-04-08","arxiv_id":"2304.03946","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt4rec-a-generative-framework-for","title":"GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation","date":"2023-04-08","arxiv_id":"2304.03879","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-multi-labeled-bengali-toxic","slug":"interpretable-multi-labeled-bengali-toxic","title":"Interpretable Multi Labeled Bengali Toxic Comments Classification using Deep Learning","date":"2023-04-08","arxiv_id":"2304.04087","n_code_links":1,"syntology":null}],"record_sha256":"ca44c9bf8f46966851f19ec6b0d3c95fa65d848088f93627c40d81e9831ed09c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}