{"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/39","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":39,"pages_in_order":109,"rows_per_page":100,"rows":[3801,3900],"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/38","next":"/method/attention-dropout/papers/40","papers":[{"paper":null,"slug":"finllms-a-framework-for-financial-reasoning","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","date":"2024-01-19","arxiv_id":"2401.10744","n_code_links":0,"syntology":null},{"paper":"/paper/langbridge-multilingual-reasoning-without","slug":"langbridge-multilingual-reasoning-without","title":"LangBridge: Multilingual Reasoning Without Multilingual Supervision","date":"2024-01-19","arxiv_id":"2401.10695","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":3,"n_instrument":2,"unverified":7,"pointer_only":12,"phrase":"5 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; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["kaistAI/LangBridge"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/mining-experimental-data-from-materials","slug":"mining-experimental-data-from-materials","title":"Mining experimental data from Materials Science literature with Large Language Models: an evaluation study","date":"2024-01-19","arxiv_id":"2401.11052","n_code_links":1,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-question-answering","title":"Reinforcement learning for question answering in programming domain using public community scoring as a human feedback","date":"2024-01-19","arxiv_id":"2401.10882","n_code_links":0,"syntology":null},{"paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","slug":"chatqa-building-gpt-4-level-conversational-qa","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","date":"2024-01-18","arxiv_id":"2401.10225","n_code_links":0,"syntology":null},{"paper":"/paper/code-prompting-elicits-conditional-reasoning","slug":"code-prompting-elicits-conditional-reasoning","title":"Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs","date":"2024-01-18","arxiv_id":"2401.10065","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["ukplab/arxiv2024-conditional-reasoning-llms"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gender-bias-in-machine-translation-and-the","title":"Gender Bias in Machine Translation and The Era of Large Language Models","date":"2024-01-18","arxiv_id":"2401.10016","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-translation-as-diffusion-visual","title":"Image Translation as Diffusion Visual Programmers","date":"2024-01-18","arxiv_id":"2401.09742","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-biases-in-large-language-models","title":"Leveraging Biases in Large Language Models: \"bias-kNN'' for Effective Few-Shot Learning","date":"2024-01-18","arxiv_id":"2401.09783","n_code_links":0,"syntology":null},{"paper":"/paper/when-neural-code-completion-models-size-up","slug":"when-neural-code-completion-models-size-up","title":"When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference","date":"2024-01-18","arxiv_id":"2401.09964","n_code_links":1,"syntology":null},{"paper":null,"slug":"bertologynavigator-advanced-question","title":"BERTologyNavigator: Advanced Question Answering with BERT-based Semantics","date":"2024-01-17","arxiv_id":"2401.09553","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-textual-authenticity-a","slug":"deciphering-textual-authenticity-a","title":"Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text","date":"2024-01-17","arxiv_id":"2401.09407","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-slot-labelling","title":"Efficient slot labelling","date":"2024-01-17","arxiv_id":"2401.09343","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-classification-performance-with","title":"Improving Classification Performance With Human Feedback: Label a few, we label the rest","date":"2024-01-17","arxiv_id":"2401.09555","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-emotions-demographic","slug":"learning-from-emotions-demographic","title":"Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues","date":"2024-01-17","arxiv_id":"2401.09248","n_code_links":1,"syntology":null},{"paper":null,"slug":"mada-meta-adaptive-optimizers-through-hyper","title":"MADA: Meta-Adaptive Optimizers through hyper-gradient Descent","date":"2024-01-17","arxiv_id":"2401.08893","n_code_links":0,"syntology":null},{"paper":"/paper/vision-mamba-efficient-visual-representation","slug":"vision-mamba-efficient-visual-representation","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","date":"2024-01-17","arxiv_id":"2401.09417","n_code_links":15,"syntology":{"ran":8,"of":13,"n_ran_checked":7,"n_instrument":1,"unverified":5,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hustvl/vim"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/a-reproducibility-study-of-goldilocks-just","slug":"a-reproducibility-study-of-goldilocks-just","title":"A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR","date":"2024-01-16","arxiv_id":"2401.08104","n_code_links":1,"syntology":null},{"paper":null,"slug":"application-of-llm-agents-in-recruitment-a","title":"Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening","date":"2024-01-16","arxiv_id":"2401.08315","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-robustness-of-llm-synthetic-text","title":"Enhancing Robustness of LLM-Synthetic Text Detectors for Academic Writing: A Comprehensive Analysis","date":"2024-01-16","arxiv_id":"2401.08046","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-inter-layer-expert-affinity-for","slug":"exploiting-inter-layer-expert-affinity-for","title":"Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference","date":"2024-01-16","arxiv_id":"2401.08383","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag-vs-fine-tuning-pipelines-tradeoffs-and-a","title":"RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture","date":"2024-01-16","arxiv_id":"2401.08406","n_code_links":0,"syntology":null},{"paper":"/paper/rotbench-a-multi-level-benchmark-for","slug":"rotbench-a-multi-level-benchmark-for","title":"RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning","date":"2024-01-16","arxiv_id":"2401.08326","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["junjie-ye/rotbench"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/tuning-language-models-by-proxy","slug":"tuning-language-models-by-proxy","title":"Tuning Language Models by Proxy","date":"2024-01-16","arxiv_id":"2401.08565","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alisawuffles/proxy-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-character-based-steganography-using-masked","slug":"a-character-based-steganography-using-masked","title":"A character-based steganography using masked language modeling","date":"2024-01-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-approach-for-automatic-program-repair","slug":"a-novel-approach-for-automatic-program-repair","title":"A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language Models","date":"2024-01-15","arxiv_id":"2401.07994","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-database-while-computationally","title":"Graph database while computationally efficient filters out quickly the ESG integrated equities in investment management","date":"2024-01-15","arxiv_id":"2401.07483","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-external-knowledge-resources-to","slug":"leveraging-external-knowledge-resources-to","title":"Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings","date":"2024-01-15","arxiv_id":"2401.07977","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["saptarshi059/cdqa-project"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-the-power-of-transformers-for","title":"Leveraging the power of transformers for guilt detection in text","date":"2024-01-15","arxiv_id":"2401.07414","n_code_links":0,"syntology":null},{"paper":"/paper/semeval-2017-task-4-sentiment-analysis-in","slug":"semeval-2017-task-4-sentiment-analysis-in","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter using BERT","date":"2024-01-15","arxiv_id":"2401.07944","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-chronicles-of-rag-the-retriever-the-chunk","title":"The Chronicles of RAG: The Retriever, the Chunk and the Generator","date":"2024-01-15","arxiv_id":"2401.07883","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-ythdf2-mediated-mrna","slug":"understanding-ythdf2-mediated-mrna","title":"Understanding YTHDF2-mediated mRNA Degradation By m6A-BERT-Deg","date":"2024-01-15","arxiv_id":"2401.08004","n_code_links":1,"syntology":null},{"paper":"/paper/harnessing-large-language-models-over","slug":"harnessing-large-language-models-over","title":"Harnessing Large Language Models Over Transformer Models for Detecting Bengali Depressive Social Media Text: A Comprehensive Study","date":"2024-01-14","arxiv_id":"2401.07310","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-be-homo-economicus-can-an-llm","title":"Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice","date":"2024-01-14","arxiv_id":"2401.07345","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapgpt-map-guided-prompting-for-unified","title":"MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation","date":"2024-01-14","arxiv_id":"2401.07314","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptformer-prompted-conformer-transducer","title":"Promptformer: Prompted Conformer Transducer for ASR","date":"2024-01-14","arxiv_id":"2401.07360","n_code_links":0,"syntology":null},{"paper":null,"slug":"streamlining-the-selection-phase-of","title":"Streamlining the Selection Phase of Systematic Literature Reviews (SLRs) Using AI-Enabled GPT-4 Assistant API","date":"2024-01-14","arxiv_id":"2402.18582","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-multi-stage-prompting-approach-for","slug":"a-novel-multi-stage-prompting-approach-for","title":"A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPT","date":"2024-01-13","arxiv_id":"2401.07098","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-in-mechanical","title":"Assessing Large Language Models in Mechanical Engineering Education: A Study on Mechanics-Focused Conceptual Understanding","date":"2024-01-13","arxiv_id":"2401.12983","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-preference-gap-between","title":"Bridging the Preference Gap between Retrievers and LLMs","date":"2024-01-13","arxiv_id":"2401.06954","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-confidence-elicitation-and-sample","title":"Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation","date":"2024-01-13","arxiv_id":"2401.08694","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-investigation-of-structures-responsible","title":"An investigation of structures responsible for gender bias in BERT and DistilBERT","date":"2024-01-12","arxiv_id":"2401.06495","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-gpt-4-and-open-source-language","title":"Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation","date":"2024-01-12","arxiv_id":"2401.06920","n_code_links":0,"syntology":null},{"paper":"/paper/from-automation-to-augmentation-large","slug":"from-automation-to-augmentation-large","title":"Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs","date":"2024-01-12","arxiv_id":"2401.06431","n_code_links":1,"syntology":null},{"paper":"/paper/how-johnny-can-persuade-llms-to-jailbreak","slug":"how-johnny-can-persuade-llms-to-jailbreak","title":"How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs","date":"2024-01-12","arxiv_id":"2401.06373","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["chats-lab/persuasive_jailbreaker"],"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/improved-learned-sparse-retrieval-with-corpus","slug":"improved-learned-sparse-retrieval-with-corpus","title":"Improved Learned Sparse Retrieval with Corpus-Specific Vocabularies","date":"2024-01-12","arxiv_id":"2401.06703","n_code_links":1,"syntology":null},{"paper":"/paper/intention-analysis-prompting-makes-large","slug":"intention-analysis-prompting-makes-large","title":"Intention Analysis Makes LLMs A Good Jailbreak Defender","date":"2024-01-12","arxiv_id":"2401.06561","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":["alphadl/safellm_with_intentionanalysis"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/mapping-transformer-leveraged-embeddings-for","slug":"mapping-transformer-leveraged-embeddings-for","title":"Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation","date":"2024-01-12","arxiv_id":"2401.06583","n_code_links":1,"syntology":null},{"paper":"/paper/mission-impossible-language-models","slug":"mission-impossible-language-models","title":"Mission: Impossible Language Models","date":"2024-01-12","arxiv_id":"2401.06416","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["jkallini/mission-impossible-language-models"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"persianmind-a-cross-lingual-persian-english","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","date":"2024-01-12","arxiv_id":"2401.06466","n_code_links":0,"syntology":null},{"paper":"/paper/pizzacommonsense-learning-to-model","slug":"pizzacommonsense-learning-to-model","title":"PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes","date":"2024-01-12","arxiv_id":"2401.06930","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-regional-impacts-of-climate-change","title":"Analyzing Regional Impacts of Climate Change using Natural Language Processing Techniques","date":"2024-01-11","arxiv_id":"2401.06817","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-data-contamination-for-pre","title":"Investigating Data Contamination for Pre-training Language Models","date":"2024-01-11","arxiv_id":"2401.06059","n_code_links":0,"syntology":null},{"paper":null,"slug":"mutation-based-consistency-testing-for","title":"Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs","date":"2024-01-11","arxiv_id":"2401.05940","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-based-mental-health-screening-from","title":"Prompt-based mental health screening from social media text","date":"2024-01-11","arxiv_id":"2401.05912","n_code_links":0,"syntology":null},{"paper":"/paper/the-benefits-of-a-concise-chain-of-thought-on","slug":"the-benefits-of-a-concise-chain-of-thought-on","title":"The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models","date":"2024-01-11","arxiv_id":"2401.05618","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["matthewrenze/jhu-concise-cot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/autoact-automatic-agent-learning-from-scratch","slug":"autoact-automatic-agent-learning-from-scratch","title":"AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning","date":"2024-01-10","arxiv_id":"2401.05268","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zjunlp/autoact"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/i-am-a-strange-dataset-metalinguistic-tests","slug":"i-am-a-strange-dataset-metalinguistic-tests","title":"I am a Strange Dataset: Metalinguistic Tests for Language Models","date":"2024-01-10","arxiv_id":"2401.05300","n_code_links":1,"syntology":null},{"paper":"/paper/infiagent-dabench-evaluating-agents-on-data","slug":"infiagent-dabench-evaluating-agents-on-data","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","date":"2024-01-10","arxiv_id":"2401.05507","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["infiagent/infiagent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"machine-teaching-for-building-modular-ai","title":"Can Active Label Correction Improve LLM-based Modular AI Systems?","date":"2024-01-10","arxiv_id":"2401.05467","n_code_links":0,"syntology":null},{"paper":null,"slug":"monte-carlo-tree-search-for-recipe-generation","title":"Monte Carlo Tree Search for Recipe Generation using GPT-2","date":"2024-01-10","arxiv_id":"2401.05199","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-for-optimizing-rag-for","title":"Reinforcement Learning for Optimizing RAG for Domain Chatbots","date":"2024-01-10","arxiv_id":"2401.06800","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-assessment-on-comprehending-mental-health","title":"An Assessment on Comprehending Mental Health through Large Language Models","date":"2024-01-09","arxiv_id":"2401.04592","n_code_links":0,"syntology":null},{"paper":"/paper/depressionemo-a-novel-dataset-for-multilabel","slug":"depressionemo-a-novel-dataset-for-multilabel","title":"DepressionEmo: A novel dataset for multilabel classification of depression emotions","date":"2024-01-09","arxiv_id":"2401.04655","n_code_links":1,"syntology":null},{"paper":null,"slug":"fighting-fire-with-fire-adversarial-prompting","title":"Fighting Fire with Fire: Adversarial Prompting to Generate a Misinformation Detection Dataset","date":"2024-01-09","arxiv_id":"2401.04481","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-detection-for-transliterated-content","title":"Language Detection for Transliterated Content","date":"2024-01-09","arxiv_id":"2401.04619","n_code_links":0,"syntology":null},{"paper":null,"slug":"phishing-website-detection-through-multi","title":"Phishing Website Detection through Multi-Model Analysis of HTML Content","date":"2024-01-09","arxiv_id":"2401.04820","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-spatial-reasoning-in-large-language","slug":"advancing-spatial-reasoning-in-large-language","title":"Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark","date":"2024-01-08","arxiv_id":"2401.03991","n_code_links":1,"syntology":null},{"paper":"/paper/anatomy-of-neural-language-models","slug":"anatomy-of-neural-language-models","title":"Anatomy of Neural Language Models","date":"2024-01-08","arxiv_id":"2401.03797","n_code_links":1,"syntology":null},{"paper":null,"slug":"distortions-in-judged-spatial-relations-in","title":"Distortions in Judged Spatial Relations in Large Language Models","date":"2024-01-08","arxiv_id":"2401.04218","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-bioinformatics","title":"Advancing bioinformatics with large language models: components, applications and perspectives","date":"2024-01-08","arxiv_id":"2401.04155","n_code_links":0,"syntology":null},{"paper":"/paper/llm4plc-harnessing-large-language-models-for","slug":"llm4plc-harnessing-large-language-models-for","title":"LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems","date":"2024-01-08","arxiv_id":"2401.05443","n_code_links":1,"syntology":null},{"paper":"/paper/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","n_code_links":6,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"roberturk-adjusting-roberta-for-turkish","title":"RoBERTurk: Adjusting RoBERTa for Turkish","date":"2024-01-07","arxiv_id":"2401.03515","n_code_links":0,"syntology":null},{"paper":null,"slug":"d-causal-exploring-defeasibility-in-causal","title":"Exploring Defeasibility in Causal Reasoning","date":"2024-01-06","arxiv_id":"2401.03183","n_code_links":0,"syntology":null},{"paper":null,"slug":"pixar-auto-regressive-language-modeling-in","title":"PIXAR: Auto-Regressive Language Modeling in Pixel Space","date":"2024-01-06","arxiv_id":"2401.03321","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-assess-tutors","title":"Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errors","date":"2024-01-06","arxiv_id":"2401.03238","n_code_links":0,"syntology":null},{"paper":"/paper/ast-t5-structure-aware-pretraining-for-code","slug":"ast-t5-structure-aware-pretraining-for-code","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","date":"2024-01-05","arxiv_id":"2401.03003","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["gonglinyuan/ast_t5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/comparative-analysis-of-llama-and-chatgpt","slug":"comparative-analysis-of-llama-and-chatgpt","title":"Can Large Language Models Understand Molecules?","date":"2024-01-05","arxiv_id":"2402.00024","n_code_links":2,"syntology":null},{"paper":"/paper/deepseek-llm-scaling-open-source-language","slug":"deepseek-llm-scaling-open-source-language","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","date":"2024-01-05","arxiv_id":"2401.02954","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-large-language-models-are","title":"Natural Language Programming in Medicine: Administering Evidence Based Clinical Workflows with Autonomous Agents Powered by Generative Large Language Models","date":"2024-01-05","arxiv_id":"2401.02851","n_code_links":0,"syntology":null},{"paper":"/paper/german-text-embedding-clustering-benchmark","slug":"german-text-embedding-clustering-benchmark","title":"German Text Embedding Clustering Benchmark","date":"2024-01-05","arxiv_id":"2401.02709","n_code_links":1,"syntology":null},{"paper":"/paper/parameter-efficient-sparsity-crafting-from","slug":"parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","n_code_links":2,"syntology":null},{"paper":null,"slug":"are-llms-robust-for-spoken-dialogues","title":"Are LLMs Robust for Spoken Dialogues?","date":"2024-01-04","arxiv_id":"2401.02297","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-extraction-contextualising-tabular","title":"Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models","date":"2024-01-04","arxiv_id":"2401.02333","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-indicnews-news-based-short-text-and","slug":"l3cube-indicnews-news-based-short-text-and","title":"L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic Languages","date":"2024-01-04","arxiv_id":"2401.02254","n_code_links":1,"syntology":null},{"paper":null,"slug":"re-evaluating-the-memory-balanced-pipeline","title":"Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe","date":"2024-01-04","arxiv_id":"2401.02088","n_code_links":0,"syntology":null},{"paper":"/paper/text2mdt-extracting-medical-decision-trees","slug":"text2mdt-extracting-medical-decision-trees","title":"Text2MDT: Extracting Medical Decision Trees from Medical Texts","date":"2024-01-04","arxiv_id":"2401.02034","n_code_links":1,"syntology":null},{"paper":"/paper/a-first-look-at-information-highlighting-in","slug":"a-first-look-at-information-highlighting-in","title":"Studying and Recommending Information Highlighting in Stack Overflow Answers","date":"2024-01-03","arxiv_id":"2401.01472","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-multilingual-information-retrieval","title":"Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprise","date":"2024-01-03","arxiv_id":"2401.01511","n_code_links":0,"syntology":null},{"paper":null,"slug":"iot-in-the-era-of-generative-ai-vision-and","title":"The Internet of Things in the Era of Generative AI: Vision and Challenges","date":"2024-01-03","arxiv_id":"2401.01923","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-mask-filling-an-effective-text","title":"Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling","date":"2024-01-03","arxiv_id":"2401.01830","n_code_links":0,"syntology":null},{"paper":null,"slug":"mlps-compass-what-is-learned-when-mlps-are","title":"MLPs Compass: What is learned when MLPs are combined with PLMs?","date":"2024-01-03","arxiv_id":"2401.01667","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-processing-and-multimodal","title":"Natural Language Processing and Multimodal Stock Price Prediction","date":"2024-01-03","arxiv_id":"2401.01487","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-zero-shot-abstractive","slug":"revisiting-zero-shot-abstractive","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","date":"2024-01-03","arxiv_id":"2401.01989","n_code_links":1,"syntology":null},{"paper":null,"slug":"token-propagation-controller-for-efficient","title":"TPC-ViT: Token Propagation Controller for Efficient Vision Transformer","date":"2024-01-03","arxiv_id":"2401.01470","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-semantic-segmentation-against","title":"Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement","date":"2024-01-03","arxiv_id":"2401.01750","n_code_links":0,"syntology":null},{"paper":"/paper/vietnamese-poem-generation-the-prospect-of","slug":"vietnamese-poem-generation-the-prospect-of","title":"Vietnamese Poem Generation & The Prospect Of Cross-Language Poem-To-Poem Translation","date":"2024-01-02","arxiv_id":"2401.01078","n_code_links":1,"syntology":null},{"paper":"/paper/a-b-b-a-triggering-logical-reasoning-failures","slug":"a-b-b-a-triggering-logical-reasoning-failures","title":"LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models","date":"2024-01-01","arxiv_id":"2401.00757","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["yxwan123/logicasker"],"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/a-computational-framework-for-behavioral","slug":"a-computational-framework-for-behavioral","title":"A Computational Framework for Behavioral Assessment of LLM Therapists","date":"2024-01-01","arxiv_id":"2401.00820","n_code_links":1,"syntology":null}],"record_sha256":"02fec438d4375385d564f05c3f68871479f3f6e77181a638d263c798c015ba64","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}