{"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/32","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":32,"pages_in_order":109,"rows_per_page":100,"rows":[3101,3200],"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/31","next":"/method/attention-dropout/papers/33","papers":[{"paper":null,"slug":"prism-patient-records-interpretation-for","title":"PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching using Large Language Models","date":"2024-04-23","arxiv_id":"2404.15549","n_code_links":0,"syntology":null},{"paper":null,"slug":"science-written-by-generative-ai-is-perceived","title":"From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science","date":"2024-04-23","arxiv_id":"2405.00706","n_code_links":0,"syntology":null},{"paper":null,"slug":"talk-too-much-poisoning-large-language-models","title":"Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models","date":"2024-04-23","arxiv_id":"2404.14795","n_code_links":0,"syntology":null},{"paper":"/paper/the-power-of-the-noisy-channel-unsupervised","slug":"the-power-of-the-noisy-channel-unsupervised","title":"Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel","date":"2024-04-23","arxiv_id":"2404.15219","n_code_links":1,"syntology":null},{"paper":"/paper/automated-long-answer-grading-with-ricechem","slug":"automated-long-answer-grading-with-ricechem","title":"Automated Long Answer Grading with RiceChem Dataset","date":"2024-04-22","arxiv_id":"2404.14316","n_code_links":1,"syntology":null},{"paper":"/paper/calc-cmu-at-semeval-2024-task-7-pre-calc","slug":"calc-cmu-at-semeval-2024-task-7-pre-calc","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","date":"2024-04-22","arxiv_id":"2404.14355","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["calc-cmu/pre-calc"],"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":"generating-attractive-and-authentic","title":"Generating Attractive and Authentic Copywriting from Customer Reviews","date":"2024-04-22","arxiv_id":"2404.13906","n_code_links":0,"syntology":null},{"paper":"/paper/how-well-can-llms-echo-us-evaluating-ai","slug":"how-well-can-llms-echo-us-evaluating-ai","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","date":"2024-04-22","arxiv_id":"2404.13957","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":6,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cuhk-arise/echo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"information-re-organization-improves","title":"Information Re-Organization Improves Reasoning in Large Language Models","date":"2024-04-22","arxiv_id":"2404.13985","n_code_links":0,"syntology":null},{"paper":"/paper/llms-know-what-they-need-leveraging-a-missing","slug":"llms-know-what-they-need-leveraging-a-missing","title":"LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation","date":"2024-04-22","arxiv_id":"2404.14043","n_code_links":1,"syntology":null},{"paper":null,"slug":"marking-visual-grading-with-highlighting","title":"Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits","date":"2024-04-22","arxiv_id":"2404.14301","n_code_links":0,"syntology":null},{"paper":null,"slug":"navigating-the-path-of-writing-outline-guided","title":"Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models","date":"2024-04-22","arxiv_id":"2404.13919","n_code_links":0,"syntology":null},{"paper":"/paper/phi-3-technical-report-a-highly-capable","slug":"phi-3-technical-report-a-highly-capable","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","date":"2024-04-22","arxiv_id":"2404.14219","n_code_links":0,"syntology":null},{"paper":"/paper/typos-that-broke-the-rag-s-back-genetic","slug":"typos-that-broke-the-rag-s-back-genetic","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","date":"2024-04-22","arxiv_id":"2404.13948","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":["zomss/garag"],"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/what-do-transformers-know-about-government","slug":"what-do-transformers-know-about-government","title":"What do Transformers Know about Government?","date":"2024-04-22","arxiv_id":"2404.14270","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-cross-lingual-stance-detection-via","slug":"zero-shot-cross-lingual-stance-detection-via","title":"Zero-shot Cross-lingual Stance Detection via Adversarial Language Adaptation","date":"2024-04-22","arxiv_id":"2404.14339","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-text-mining-of-experimental","title":"Automated Text Mining of Experimental Methodologies from Biomedical Literature","date":"2024-04-21","arxiv_id":"2404.13779","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-retrieval-quality-in-retrieval","slug":"evaluating-retrieval-quality-in-retrieval","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","date":"2024-04-21","arxiv_id":"2404.13781","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alirezasalemi7/erag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/svgeditbench-a-benchmark-dataset-for","slug":"svgeditbench-a-benchmark-dataset-for","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","date":"2024-04-21","arxiv_id":"2404.13710","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["mti-lab/svgeditbench"],"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":"bert-accelerating-vital-signs-measurement-for","title":"BERT: Accelerating Vital Signs Measurement for Bioradar with An Efficient Recursive Technique","date":"2024-04-20","arxiv_id":"2404.13315","n_code_links":0,"syntology":null},{"paper":"/paper/do-english-named-entity-recognizers-work-well","slug":"do-english-named-entity-recognizers-work-well","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","date":"2024-04-20","arxiv_id":"2404.13465","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-subword-tokenization-alien-subword","slug":"evaluating-subword-tokenization-alien-subword","title":"Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge","date":"2024-04-20","arxiv_id":"2404.13292","n_code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-based-relation","slug":"retrieval-augmented-generation-based-relation","title":"Retrieval-Augmented Generation-based Relation Extraction","date":"2024-04-20","arxiv_id":"2404.13397","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-alignment-for-zero-shot-concept","title":"Data Alignment for Zero-Shot Concept Generation in Dermatology AI","date":"2024-04-19","arxiv_id":"2404.13043","n_code_links":0,"syntology":null},{"paper":"/paper/dubo-sql-diverse-retrieval-augmented","slug":"dubo-sql-diverse-retrieval-augmented","title":"Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL","date":"2024-04-19","arxiv_id":"2404.12560","n_code_links":1,"syntology":null},{"paper":null,"slug":"enabling-natural-zero-shot-prompting-on","title":"Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning","date":"2024-04-19","arxiv_id":"2404.12897","n_code_links":0,"syntology":null},{"paper":"/paper/multi-class-depression-detection-through","slug":"multi-class-depression-detection-through","title":"Multi Class Depression Detection Through Tweets using Artificial Intelligence","date":"2024-04-19","arxiv_id":"2404.13104","n_code_links":1,"syntology":null},{"paper":"/paper/the-instruction-hierarchy-training-llms-to","slug":"the-instruction-hierarchy-training-llms-to","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","date":"2024-04-19","arxiv_id":"2404.13208","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-multi-view-insights-in-knowledge","title":"Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation","date":"2024-04-19","arxiv_id":"2404.12879","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-emotion-features-in-irony","title":"Augmenting emotion features in irony detection with Large language modeling","date":"2024-04-18","arxiv_id":"2404.12291","n_code_links":0,"syntology":null},{"paper":null,"slug":"emrqa-msquad-a-medical-dataset-structured","title":"emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information","date":"2024-04-18","arxiv_id":"2404.12050","n_code_links":0,"syntology":null},{"paper":"/paper/from-form-s-to-meaning-probing-the-semantic","slug":"from-form-s-to-meaning-probing-the-semantic","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","date":"2024-04-18","arxiv_id":"2404.12145","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/multisense_consistency"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"irag-an-incremental-retrieval-augmented","title":"iRAG: Advancing RAG for Videos with an Incremental Approach","date":"2024-04-18","arxiv_id":"2404.12309","n_code_links":0,"syntology":null},{"paper":"/paper/longembed-extending-embedding-models-for-long","slug":"longembed-extending-embedding-models-for-long","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","date":"2024-04-18","arxiv_id":"2404.12096","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dwzhu-pku/longembed"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"midget-music-conditioned-3d-dance-generation","title":"MIDGET: Music Conditioned 3D Dance Generation","date":"2024-04-18","arxiv_id":"2404.12062","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragar-your-falsehood-radar-rag-augmented","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","date":"2024-04-18","arxiv_id":"2404.12065","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragcache-efficient-knowledge-caching-for","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","date":"2024-04-18","arxiv_id":"2404.12457","n_code_links":0,"syntology":null},{"paper":null,"slug":"ram-towards-an-ever-improving-memory-system","title":"RAM: Towards an Ever-Improving Memory System by Learning from Communications","date":"2024-04-18","arxiv_id":"2404.12045","n_code_links":0,"syntology":null},{"paper":null,"slug":"stance-detection-on-social-media-with-fine","title":"Stance Detection on Social Media with Fine-Tuned Large Language Models","date":"2024-04-18","arxiv_id":"2404.12171","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-retrieval-augmented-text-1","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","date":"2024-04-17","arxiv_id":"2404.10981","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-analysis-of-deep-natural-networks","slug":"comparative-analysis-of-deep-natural-networks","title":"Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"demystifying-legalese-an-automated-approach","title":"Demystifying Legalese: An Automated Approach for Summarizing and Analyzing Overlaps in Privacy Policies and Terms of Service","date":"2024-04-17","arxiv_id":"2404.13087","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-q-a-with-domain-specific-fine","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","date":"2024-04-17","arxiv_id":"2404.11792","n_code_links":0,"syntology":null},{"paper":null,"slug":"improvement-in-semantic-address-matching","title":"Improvement in Semantic Address Matching using Natural Language Processing","date":"2024-04-17","arxiv_id":"2404.11691","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sentiment-analysis-of-medical-text-based-on","title":"A Sentiment Analysis of Medical Text Based on Deep Learning","date":"2024-04-16","arxiv_id":"2404.10503","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesjudge-bayesian-kernel-language-modelling","title":"BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction","date":"2024-04-16","arxiv_id":"2404.10481","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-interdisciplinary-research-with","title":"Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling","date":"2024-04-16","arxiv_id":"2404.13078","n_code_links":0,"syntology":null},{"paper":"/paper/ladic-are-diffusion-models-really-inferior-to","slug":"ladic-are-diffusion-models-really-inferior-to","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","date":"2024-04-16","arxiv_id":"2404.10763","n_code_links":1,"syntology":null},{"paper":null,"slug":"relational-graph-convolutional-networks-for-1","title":"Relational Graph Convolutional Networks for Sentiment Analysis","date":"2024-04-16","arxiv_id":"2404.13079","n_code_links":0,"syntology":null},{"paper":"/paper/spiral-of-silences-how-is-large-language","slug":"spiral-of-silences-how-is-large-language","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10496","n_code_links":1,"syntology":null},{"paper":"/paper/aesexpert-towards-multi-modality-foundation","slug":"aesexpert-towards-multi-modality-foundation","title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception","date":"2024-04-15","arxiv_id":"2404.09624","n_code_links":1,"syntology":null},{"paper":null,"slug":"deceiving-to-enlighten-coaxing-llms-to-self","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","date":"2024-04-15","arxiv_id":"2404.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-ai-generated-text-based-on-nlp-and","title":"Detecting AI Generated Text Based on NLP and Machine Learning Approaches","date":"2024-04-15","arxiv_id":"2404.10032","n_code_links":0,"syntology":null},{"paper":null,"slug":"quality-assessment-of-prompts-used-in-code","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","date":"2024-04-15","arxiv_id":"2404.10155","n_code_links":0,"syntology":null},{"paper":"/paper/s-gpts-a-new-approach-to-autoregressive","slug":"s-gpts-a-new-approach-to-autoregressive","title":"σ-GPTs: A New Approach to Autoregressive Models","date":"2024-04-15","arxiv_id":"2404.09562","n_code_links":1,"syntology":null},{"paper":"/paper/bert-lsh-reducing-absolute-compute-for","slug":"bert-lsh-reducing-absolute-compute-for","title":"BERT-LSH: Reducing Absolute Compute For Attention","date":"2024-04-12","arxiv_id":"2404.08836","n_code_links":1,"syntology":null},{"paper":null,"slug":"creativeval-evaluating-creativity-of-llm","title":"CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation","date":"2024-04-12","arxiv_id":"2404.08806","n_code_links":0,"syntology":null},{"paper":"/paper/fastlogad-log-anomaly-detection-with-mask","slug":"fastlogad-log-anomaly-detection-with-mask","title":"FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination","date":"2024-04-12","arxiv_id":"2404.08750","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-chatgpt-transforming-academics-writing","title":"Is ChatGPT Transforming Academics' Writing Style?","date":"2024-04-12","arxiv_id":"2404.08627","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-small-base-lms-with-fewer-tokens","slug":"pre-training-small-base-lms-with-fewer-tokens","title":"Inheritune: Training Smaller Yet More Attentive Language Models","date":"2024-04-12","arxiv_id":"2404.08634","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sanyalsunny111/llm-inheritune"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reducing-hallucination-in-structured-outputs","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","date":"2024-04-12","arxiv_id":"2404.08189","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-code-similarity-evaluation-with","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","date":"2024-04-12","arxiv_id":"2404.08817","n_code_links":0,"syntology":null},{"paper":"/paper/small-models-are-still-effective-cross-domain","slug":"small-models-are-still-effective-cross-domain","title":"Small Models Are (Still) Effective Cross-Domain Argument Extractors","date":"2024-04-12","arxiv_id":"2404.08579","n_code_links":1,"syntology":null},{"paper":"/paper/amplegcg-learning-a-universal-and","slug":"amplegcg-learning-a-universal-and","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","date":"2024-04-11","arxiv_id":"2404.07921","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-information-retrieval-evaluation","title":"Generative Information Retrieval Evaluation","date":"2024-04-11","arxiv_id":"2404.08137","n_code_links":0,"syntology":null},{"paper":null,"slug":"hltcoe-at-trec-2023-neuclir-track","title":"HLTCOE at TREC 2023 NeuCLIR Track","date":"2024-04-11","arxiv_id":"2404.08118","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-mt5-an-open-source-multilingual-text","title":"Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain","date":"2024-04-11","arxiv_id":"2404.07613","n_code_links":0,"syntology":null},{"paper":"/paper/on-training-data-influence-of-gpt-models","slug":"on-training-data-influence-of-gpt-models","title":"On Training Data Influence of GPT Models","date":"2024-04-11","arxiv_id":"2404.07840","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["eleutherai/pythia","ernie-research/gptfluence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rumour-evaluation-with-very-large-language","slug":"rumour-evaluation-with-very-large-language","title":"Rumour Evaluation with Very Large Language Models","date":"2024-04-11","arxiv_id":"2404.16859","n_code_links":1,"syntology":null},{"paper":"/paper/control-dag-constrained-decoding-for-non","slug":"control-dag-constrained-decoding-for-non","title":"Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata","date":"2024-04-10","arxiv_id":"2404.06854","n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-cause-pair-extraction-method-based-on","title":"Emotion-cause pair extraction method based on multi-granularity information and multi-module interaction","date":"2024-04-10","arxiv_id":"2404.06812","n_code_links":0,"syntology":null},{"paper":"/paper/llama-vits-enhancing-tts-synthesis-with","slug":"llama-vits-enhancing-tts-synthesis-with","title":"Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness","date":"2024-04-10","arxiv_id":"2404.06714","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["xincanfeng/vitsgpt"],"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/not-all-contexts-are-equal-teaching-llms","slug":"not-all-contexts-are-equal-teaching-llms","title":"Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation","date":"2024-04-10","arxiv_id":"2404.06809","n_code_links":1,"syntology":null},{"paper":"/paper/simpler-becomes-harder-do-llms-exhibit-a","slug":"simpler-becomes-harder-do-llms-exhibit-a","title":"Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora?","date":"2024-04-10","arxiv_id":"2404.06838","n_code_links":1,"syntology":null},{"paper":"/paper/superposition-prompting-improving-and","slug":"superposition-prompting-improving-and","title":"Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation","date":"2024-04-10","arxiv_id":"2404.06910","n_code_links":1,"syntology":null},{"paper":"/paper/all-in-one-an-empirical-study-of-gpt-for-few","slug":"all-in-one-an-empirical-study-of-gpt-for-few","title":"Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis","date":"2024-04-09","arxiv_id":"2404.06063","n_code_links":1,"syntology":null},{"paper":null,"slug":"characterizing-multimodal-long-form","title":"Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports","date":"2024-04-09","arxiv_id":"2404.06162","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-potential-of-large-foundation","slug":"exploring-the-potential-of-large-foundation","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","date":"2024-04-09","arxiv_id":"2404.06194","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["ltttpku/cmd-se-release"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-pre-trained-transformer-for-2","title":"Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning","date":"2024-04-09","arxiv_id":"2404.06330","n_code_links":0,"syntology":null},{"paper":null,"slug":"sandwich-attack-multi-language-mixture","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","date":"2024-04-09","arxiv_id":"2404.07242","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-study-on-german-language-models","title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding","date":"2024-04-08","arxiv_id":"2404.05694","n_code_links":0,"syntology":null},{"paper":null,"slug":"constraining-large-language-model-for","title":"Guiding Large Language Models to Generate Computer-Parsable Content","date":"2024-04-08","arxiv_id":"2404.05499","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-interventional-reasoning","title":"Evaluating Interventional Reasoning Capabilities of Large Language Models","date":"2024-04-08","arxiv_id":"2404.05545","n_code_links":0,"syntology":null},{"paper":null,"slug":"ltner-large-language-model-tagging-for-named","title":"LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity Marking","date":"2024-04-08","arxiv_id":"2404.05624","n_code_links":0,"syntology":null},{"paper":null,"slug":"medexpqa-multilingual-benchmarking-of-large","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","date":"2024-04-08","arxiv_id":"2404.05590","n_code_links":0,"syntology":null},{"paper":"/paper/petkaz-at-semeval-2024-task-3-advancing","slug":"petkaz-at-semeval-2024-task-3-advancing","title":"PetKaz at SemEval-2024 Task 3: Advancing Emotion Classification with an LLM for Emotion-Cause Pair Extraction in Conversations","date":"2024-04-08","arxiv_id":"2404.05502","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-of-language-models-part-3-3-knowledge","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","date":"2024-04-08","arxiv_id":"2404.05405","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-extraction-using-large-language","title":"Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations","date":"2024-04-08","arxiv_id":"2404.05415","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-stealth-adversarial-text-attacks-on","title":"Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods","date":"2024-04-08","arxiv_id":"2404.05159","n_code_links":0,"syntology":null},{"paper":"/paper/a-multi-level-framework-for-accelerating","slug":"a-multi-level-framework-for-accelerating","title":"A Multi-Level Framework for Accelerating Training Transformer Models","date":"2024-04-07","arxiv_id":"2404.07999","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["photooon/multi-level-training-framework"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/data-bias-according-to-bipol-men-are","slug":"data-bias-according-to-bipol-men-are","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","date":"2024-04-07","arxiv_id":"2404.04838","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-morphology-based-investigation-of","title":"A Morphology-Based Investigation of Positional Encodings","date":"2024-04-06","arxiv_id":"2404.04530","n_code_links":0,"syntology":null},{"paper":"/paper/iitk-at-semeval-2024-task-2-exploring-the","slug":"iitk-at-semeval-2024-task-2-exploring-the","title":"IITK at SemEval-2024 Task 2: Exploring the Capabilities of LLMs for Safe Biomedical Natural Language Inference for Clinical Trials","date":"2024-04-06","arxiv_id":"2404.04510","n_code_links":1,"syntology":null},{"paper":null,"slug":"recgpt-generative-personalized-prompts-for","title":"RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm","date":"2024-04-06","arxiv_id":"2404.08675","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-political-entity-sentiment-in","slug":"deciphering-political-entity-sentiment-in","title":"Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategies","date":"2024-04-05","arxiv_id":"2404.04361","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-the-robustness-of-modelling","slug":"investigating-the-robustness-of-modelling","title":"Investigating the Robustness of Modelling Decisions for Few-Shot Cross-Topic Stance Detection: A Preregistered Study","date":"2024-04-05","arxiv_id":"2404.03987","n_code_links":1,"syntology":null},{"paper":"/paper/scope-ambiguities-in-large-language-models","slug":"scope-ambiguities-in-large-language-models","title":"Scope Ambiguities in Large Language Models","date":"2024-04-05","arxiv_id":"2404.04332","n_code_links":1,"syntology":null},{"paper":"/paper/banglaautokg-automatic-bangla-knowledge-graph","slug":"banglaautokg-automatic-bangla-knowledge-graph","title":"BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering","date":"2024-04-04","arxiv_id":"2404.03528","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["azminewasi/banglaautokg"],"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/cbr-rag-case-based-reasoning-for-retrieval","slug":"cbr-rag-case-based-reasoning-for-retrieval","title":"CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering","date":"2024-04-04","arxiv_id":"2404.04302","n_code_links":1,"syntology":null},{"paper":"/paper/conflare-conformal-large-language-model","slug":"conflare-conformal-large-language-model","title":"CONFLARE: CONFormal LArge language model REtrieval","date":"2024-04-04","arxiv_id":"2404.04287","n_code_links":1,"syntology":null}],"record_sha256":"7455c2874d773a55c9901c008249911f24cb1f80898e305bf5b06a9397c9fd74","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}