{"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/26","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":26,"pages_in_order":109,"rows_per_page":100,"rows":[2501,2600],"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/25","next":"/method/attention-dropout/papers/27","papers":[{"paper":"/paper/leveraging-transformers-for-weakly-supervised","slug":"leveraging-transformers-for-weakly-supervised","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","date":"2024-07-08","arxiv_id":"2407.06018","n_code_links":1,"syntology":null},{"paper":null,"slug":"personality-analysis-for-social-media-users","title":"Personality Analysis for Social Media Users using Arabic language and its Effect on Sentiment Analysis","date":"2024-07-08","arxiv_id":"2407.06314","n_code_links":0,"syntology":null},{"paper":null,"slug":"potential-of-multimodal-large-language-models","title":"Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports","date":"2024-07-08","arxiv_id":"2407.05758","n_code_links":0,"syntology":null},{"paper":null,"slug":"surprising-gender-biases-in-gpt","title":"Surprising gender biases in GPT","date":"2024-07-08","arxiv_id":"2407.06003","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-braille-an-end-to-end-tool-for-chinese","title":"Vision-Braille: An End-to-End Tool for Chinese Braille Image-to-Text Translation","date":"2024-07-08","arxiv_id":"2407.06048","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-you-know-that-teaching-generative","slug":"how-do-you-know-that-teaching-generative","title":"How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions","date":"2024-07-06","arxiv_id":"2407.05015","n_code_links":1,"syntology":null},{"paper":"/paper/rule-reliable-multimodal-rag-for-factuality","slug":"rule-reliable-multimodal-rag-for-factuality","title":"RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models","date":"2024-07-06","arxiv_id":"2407.05131","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["richard-peng-xia/rule"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/shine-saliency-aware-hierarchical-negative","slug":"shine-saliency-aware-hierarchical-negative","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","date":"2024-07-06","arxiv_id":"2407.05118","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zxccade/shine"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vortex-under-ripplet-an-empirical-study-of","title":"Are LLMs Correctly Integrated into Software Systems?","date":"2024-07-06","arxiv_id":"2407.05138","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-strategic-decision","title":"Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games","date":"2024-07-05","arxiv_id":"2407.04467","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-vs-retro-exploring-the-intersection-of","title":"GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning","date":"2024-07-05","arxiv_id":"2407.04528","n_code_links":0,"syntology":null},{"paper":"/paper/using-llms-to-label-medical-papers-according","slug":"using-llms-to-label-medical-papers-according","title":"Using LLMs to label medical papers according to the CIViC evidence model","date":"2024-07-05","arxiv_id":"2407.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-vs-large-language-models-for","title":"Convolutional vs Large Language Models for Software Log Classification in Edge-Deployable Cellular Network Testing","date":"2024-07-04","arxiv_id":"2407.03759","n_code_links":0,"syntology":null},{"paper":"/paper/deep-content-understanding-toward-entity-and","slug":"deep-content-understanding-toward-entity-and","title":"Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation Models","date":"2024-07-04","arxiv_id":"2407.04050","n_code_links":1,"syntology":null},{"paper":null,"slug":"dslr-document-refinement-with-sentence-level","title":"DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation","date":"2024-07-04","arxiv_id":"2407.03627","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-data-to-commonsense-reasoning-the-use-of","title":"From Data to Commonsense Reasoning: The Use of Large Language Models for Explainable AI","date":"2024-07-04","arxiv_id":"2407.03778","n_code_links":0,"syntology":null},{"paper":null,"slug":"hera-high-efficiency-matrix-compression-via","title":"QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering","date":"2024-07-04","arxiv_id":"2407.03637","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrinfox-at-checkthat-2024-task-1-enhancing","title":"HYBRINFOX at CheckThat! 2024 -- Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation","date":"2024-07-04","arxiv_id":"2407.03850","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrinfox-at-checkthat-2024-task-2-enriching","title":"HYBRINFOX at CheckThat! 2024 -- Task 2: Enriching BERT Models with the Expert System VAGO for Subjectivity Detection","date":"2024-07-04","arxiv_id":"2407.03770","n_code_links":0,"syntology":null},{"paper":null,"slug":"nutribench-a-dataset-for-evaluating-large","title":"NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptions","date":"2024-07-04","arxiv_id":"2407.12843","n_code_links":0,"syntology":null},{"paper":"/paper/planning-with-large-language-models-for","slug":"planning-with-large-language-models-for","title":"Controllable Conversations: Planning-Based Dialogue Agent with Large Language Models","date":"2024-07-04","arxiv_id":"2407.03884","n_code_links":1,"syntology":null},{"paper":null,"slug":"question-analysis-prompting-improves-llm","title":"Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks","date":"2024-07-04","arxiv_id":"2407.03624","n_code_links":0,"syntology":null},{"paper":null,"slug":"slice-100k-a-multimodal-dataset-for-extrusion","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","date":"2024-07-04","arxiv_id":"2407.04180","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-automating-text-annotation-a-case","title":"Towards Automating Text Annotation: A Case Study on Semantic Proximity Annotation using GPT-4","date":"2024-07-04","arxiv_id":"2407.04130","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-dsl-code-generation","title":"A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation","date":"2024-07-03","arxiv_id":"2407.02742","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentinstruct-toward-generative-teaching-with","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","date":"2024-07-03","arxiv_id":"2407.03502","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-gradient-descent-with-generalized","slug":"automatic-gradient-descent-with-generalized","title":"Gradient descent with generalized Newton's method","date":"2024-07-03","arxiv_id":"2407.02772","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shiyunxu/autogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/catt-character-based-arabic-tashkeel","slug":"catt-character-based-arabic-tashkeel","title":"CATT: Character-based Arabic Tashkeel Transformer","date":"2024-07-03","arxiv_id":"2407.03236","n_code_links":1,"syntology":null},{"paper":null,"slug":"croppable-knowledge-graph-embedding","title":"Croppable Knowledge Graph Embedding","date":"2024-07-03","arxiv_id":"2407.02779","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-llm-abilities-in-idiomatic","title":"Improving LLM Abilities in Idiomatic Translation","date":"2024-07-03","arxiv_id":"2407.03518","n_code_links":0,"syntology":null},{"paper":null,"slug":"mlkd-bert-multi-level-knowledge-distillation","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02775","n_code_links":0,"syntology":null},{"paper":null,"slug":"obfuscatune-obfuscated-offsite-fine-tuning","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","date":"2024-07-03","arxiv_id":"2407.02960","n_code_links":0,"syntology":null},{"paper":null,"slug":"ospc-artificial-vlm-features-for-hateful-meme","title":"OSPC: Artificial VLM Features for Hateful Meme Detection","date":"2024-07-03","arxiv_id":"2407.12836","n_code_links":0,"syntology":null},{"paper":null,"slug":"rdbe-reasoning-distillation-based-evaluation","title":"RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring","date":"2024-07-03","arxiv_id":"2407.13781","n_code_links":0,"syntology":null},{"paper":null,"slug":"regurgitative-training-the-value-of-real-data","title":"Regurgitative Training: The Value of Real Data in Training Large Language Models","date":"2024-07-03","arxiv_id":"2407.12835","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-code-clone-detection-capability","title":"Assessing the Code Clone Detection Capability of Large Language Models","date":"2024-07-02","arxiv_id":"2407.02402","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-numeric-awards-in-context-dueling","title":"Beyond Numeric Awards: In-Context Dueling Bandits with LLM Agents","date":"2024-07-02","arxiv_id":"2407.01887","n_code_links":0,"syntology":null},{"paper":"/paper/extracting-and-encoding-leveraging-large","slug":"extracting-and-encoding-leveraging-large","title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation","date":"2024-07-02","arxiv_id":"2407.01948","n_code_links":1,"syntology":null},{"paper":"/paper/gptcast-a-weather-language-model-for","slug":"gptcast-a-weather-language-model-for","title":"GPTCast: a weather language model for precipitation nowcasting","date":"2024-07-02","arxiv_id":"2407.02089","n_code_links":1,"syntology":null},{"paper":null,"slug":"grasp-a-grid-based-benchmark-for-evaluating","title":"GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning","date":"2024-07-02","arxiv_id":"2407.01892","n_code_links":0,"syntology":null},{"paper":"/paper/integrate-the-essence-and-eliminate-the-dross","slug":"integrate-the-essence-and-eliminate-the-dross","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","date":"2024-07-02","arxiv_id":"2407.02056","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":["WangXinglin/FSC"],"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/mememo-on-device-retrieval-augmentation-for","slug":"mememo-on-device-retrieval-augmentation-for","title":"MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation","date":"2024-07-02","arxiv_id":"2407.01972","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-trolley-problems-for-language","slug":"multilingual-trolley-problems-for-language","title":"Language Model Alignment in Multilingual Trolley Problems","date":"2024-07-02","arxiv_id":"2407.02273","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["causalNLP/moralmachine","causalnlp/multitp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","n_code_links":0,"syntology":null},{"paper":"/paper/sop-unlock-the-power-of-social-facilitation","slug":"sop-unlock-the-power-of-social-facilitation","title":"SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters","date":"2024-07-02","arxiv_id":"2407.01902","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yang-yan-yang-yan/sop"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"the-solution-for-the-pst-kdd-2024-oag","title":"The Solution for The PST-KDD-2024 OAG-Challenge","date":"2024-07-02","arxiv_id":"2407.12827","n_code_links":0,"syntology":null},{"paper":"/paper/bergen-a-benchmarking-library-for-retrieval","slug":"bergen-a-benchmarking-library-for-retrieval","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","date":"2024-07-01","arxiv_id":"2407.01102","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver/bergen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"face4rag-factual-consistency-evaluation-for","title":"Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese","date":"2024-07-01","arxiv_id":"2407.01080","n_code_links":0,"syntology":null},{"paper":null,"slug":"ground-every-sentence-improving-retrieval","title":"Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation","date":"2024-07-01","arxiv_id":"2407.01796","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-rag-empowered-multi-modal-llm-for","title":"Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approach","date":"2024-07-01","arxiv_id":"2407.00978","n_code_links":0,"syntology":null},{"paper":"/paper/increasing-model-capacity-for-free-a-simple","slug":"increasing-model-capacity-for-free-a-simple","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","date":"2024-07-01","arxiv_id":"2407.01320","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":6,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"7 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lins-lab/capaboost"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-modal-fusion-based-multi-task-semantic","title":"Multi-Modal Fusion-Based Multi-Task Semantic Communication System","date":"2024-07-01","arxiv_id":"2407.00964","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-dc-link-capacitor-current-ripple","title":"Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models","date":"2024-07-01","arxiv_id":"2407.01724","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-in","slug":"retrieval-augmented-generation-in","title":"Retrieval-augmented generation in multilingual settings","date":"2024-07-01","arxiv_id":"2407.01463","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["naver/bergen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/searching-for-best-practices-in-retrieval","slug":"searching-for-best-practices-in-retrieval","title":"Searching for Best Practices in Retrieval-Augmented Generation","date":"2024-07-01","arxiv_id":"2407.01219","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":["FudanDNN-NLP/RAG"],"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/summary-of-a-haystack-a-challenge-to-long","slug":"summary-of-a-haystack-a-challenge-to-long","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","date":"2024-07-01","arxiv_id":"2407.01370","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["salesforce/summary-of-a-haystack"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-memory-3-language-modeling-with-explicit","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","date":"2024-07-01","arxiv_id":"2407.01178","n_code_links":0,"syntology":null},{"paper":null,"slug":"characterizing-stereotypical-bias-from","title":"Characterizing Stereotypical Bias from Privacy-preserving Pre-Training","date":"2024-06-30","arxiv_id":"2407.00764","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalturk-optimized-bert-for-multi-label-text","title":"LegalTurk Optimized BERT for Multi-Label Text Classification and NER","date":"2024-06-30","arxiv_id":"2407.00648","n_code_links":0,"syntology":null},{"paper":"/paper/parm-efficient-training-of-large-sparsely","slug":"parm-efficient-training-of-large-sparsely","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","date":"2024-06-30","arxiv_id":"2407.00599","n_code_links":1,"syntology":null},{"paper":null,"slug":"answering-real-world-clinical-questions-using","title":"Answering real-world clinical questions using large language model based systems","date":"2024-06-29","arxiv_id":"2407.00541","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-rag-to-riches-retrieval-interlaced-with","title":"From RAG to RICHES: Retrieval Interlaced with Sequence Generation","date":"2024-06-29","arxiv_id":"2407.00361","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-generated-natural-language-meets-scaling","title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods","date":"2024-06-29","arxiv_id":"2407.00322","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-rlaif-for-code-generation-with-api","title":"Applying RLAIF for Code Generation with API-usage in Lightweight LLMs","date":"2024-06-28","arxiv_id":"2406.20060","n_code_links":0,"syntology":null},{"paper":null,"slug":"fred-flexible-reduction-distribution","title":"FRED: Flexible REduction-Distribution Interconnect and Communication Implementation for Wafer-Scale Distributed Training of DNN Models","date":"2024-06-28","arxiv_id":"2406.19580","n_code_links":0,"syntology":null},{"paper":"/paper/machine-learning-predictors-for-min-entropy","slug":"machine-learning-predictors-for-min-entropy","title":"Machine Learning Predictors for Min-Entropy Estimation","date":"2024-06-28","arxiv_id":"2406.19983","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalebio-scalable-bilevel-optimization-for","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","date":"2024-06-28","arxiv_id":"2406.19976","n_code_links":0,"syntology":null},{"paper":"/paper/shortcutsbench-a-large-scale-real-world","slug":"shortcutsbench-a-large-scale-real-world","title":"ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents","date":"2024-06-28","arxiv_id":"2407.00132","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eachsheep/shortcutsbench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"uncertainty-quantification-in-large-language","title":"Uncertainty Quantification in Large Language Models Through Convex Hull Analysis","date":"2024-06-28","arxiv_id":"2406.19712","n_code_links":0,"syntology":null},{"paper":"/paper/autopuredata-automated-filtering-of-web-data","slug":"autopuredata-automated-filtering-of-web-data","title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge","date":"2024-06-27","arxiv_id":"2406.19271","n_code_links":1,"syntology":null},{"paper":null,"slug":"autorag-hp-automatic-online-hyper-parameter","title":"AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19251","n_code_links":0,"syntology":null},{"paper":"/paper/fibottention-inceptive-visual-representation","slug":"fibottention-inceptive-visual-representation","title":"Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across Heads","date":"2024-06-27","arxiv_id":"2406.19391","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuned-network-relies-on-generic","title":"Fine-tuned network relies on generic representation to solve unseen cognitive task","date":"2024-06-27","arxiv_id":"2406.18926","n_code_links":0,"syntology":null},{"paper":"/paper/from-artificial-needles-to-real-haystacks","slug":"from-artificial-needles-to-real-haystacks","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","date":"2024-06-27","arxiv_id":"2406.19292","n_code_links":1,"syntology":null},{"paper":null,"slug":"granite-function-calling-model-introducing","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","date":"2024-06-27","arxiv_id":"2407.00121","n_code_links":0,"syntology":null},{"paper":null,"slug":"historia-magistra-vitae-dynamic-topic","title":"Historia Magistra Vitae: Dynamic Topic Modeling of Roman Literature using Neural Embeddings","date":"2024-06-27","arxiv_id":"2406.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"indotoxic2024-a-demographically-enriched","title":"IndoToxic2024: A Demographically-Enriched Dataset of Hate Speech and Toxicity Types for Indonesian Language","date":"2024-06-27","arxiv_id":"2406.19349","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-depression-and-anxiety-risk-in","title":"Predicting Depression and Anxiety Risk in Dutch Neighborhoods from Street-View Images","date":"2024-06-27","arxiv_id":"2407.09547","n_code_links":0,"syntology":null},{"paper":null,"slug":"raven-multitask-retrieval-augmented-vision","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","date":"2024-06-27","arxiv_id":"2406.19150","n_code_links":0,"syntology":null},{"paper":"/paper/seakr-self-aware-knowledge-retrieval-for","slug":"seakr-self-aware-knowledge-retrieval-for","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19215","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thu-keg/seakr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"seeing-is-believing-black-box-membership","title":"Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation","date":"2024-06-27","arxiv_id":"2406.19234","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-model-arena-for-cross-lingual-sentiment","title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","n_code_links":0,"syntology":null},{"paper":null,"slug":"apigen-automated-pipeline-for-generating","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","date":"2024-06-26","arxiv_id":"2406.18518","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-quality-of-answers-for-retrieval","title":"Evaluating Quality of Answers for Retrieval-Augmented Generation: A Strong LLM Is All You Need","date":"2024-06-26","arxiv_id":"2406.18064","n_code_links":0,"syntology":null},{"paper":"/paper/factfinders-at-checkthat-2024-refining-check","slug":"factfinders-at-checkthat-2024-refining-check","title":"FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning","date":"2024-06-26","arxiv_id":"2406.18297","n_code_links":1,"syntology":null},{"paper":null,"slug":"glue-pizza-and-eat-rocks-exploiting","title":"\"Glue pizza and eat rocks\" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models","date":"2024-06-26","arxiv_id":"2406.19417","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-entity-recognition-using-ensembles","title":"Improving Entity Recognition Using Ensembles of Deep Learning and Fine-tuned Large Language Models: A Case Study on Adverse Event Extraction from Multiple Sources","date":"2024-06-26","arxiv_id":"2406.18049","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-graph-enhanced-retrieval-augmented","slug":"knowledge-graph-enhanced-retrieval-augmented","title":"Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis","date":"2024-06-26","arxiv_id":"2406.18114","n_code_links":1,"syntology":null},{"paper":"/paper/mathodyssey-benchmarking-mathematical-problem","slug":"mathodyssey-benchmarking-mathematical-problem","title":"MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data","date":"2024-06-26","arxiv_id":"2406.18321","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"multi-step-knowledge-retrieval-and-inference","title":"Multi-step Inference over Unstructured Data","date":"2024-06-26","arxiv_id":"2406.17987","n_code_links":0,"syntology":null},{"paper":null,"slug":"poisoned-langchain-jailbreak-llms-by","title":"Poisoned LangChain: Jailbreak LLMs by LangChain","date":"2024-06-26","arxiv_id":"2406.18122","n_code_links":0,"syntology":null},{"paper":"/paper/resumeatlas-revisiting-resume-classification","slug":"resumeatlas-revisiting-resume-classification","title":"ResumeAtlas: Revisiting Resume Classification with Large-Scale Datasets and Large Language Models","date":"2024-06-26","arxiv_id":"2406.18125","n_code_links":1,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","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":["dongguanting/dpa-rag"],"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":"zero-shot-prompt-based-classification-topic","title":"Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets","date":"2024-06-26","arxiv_id":"2406.18239","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-neural-information-retrieval-boolean","title":"SetBERT: Enhancing Retrieval Performance for Boolean Logic and Set Operation Queries","date":"2024-06-25","arxiv_id":"2406.17282","n_code_links":0,"syntology":null},{"paper":"/paper/ctbench-a-comprehensive-benchmark-for","slug":"ctbench-a-comprehensive-benchmark-for","title":"CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design","date":"2024-06-25","arxiv_id":"2406.17888","n_code_links":1,"syntology":null},{"paper":"/paper/interpreting-attention-layer-outputs-with","slug":"interpreting-attention-layer-outputs-with","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","date":"2024-06-25","arxiv_id":"2406.17759","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":["ckkissane/attention-output-saes"],"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/lumberchunker-long-form-narrative-document","slug":"lumberchunker-long-form-narrative-document","title":"LumberChunker: Long-Form Narrative Document Segmentation","date":"2024-06-25","arxiv_id":"2406.17526","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["joaodsmarques/lumberchunker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ragbench-explainable-benchmark-for-retrieval","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","date":"2024-06-25","arxiv_id":"2407.11005","n_code_links":0,"syntology":null},{"paper":"/paper/this-paper-had-the-smartest-reviewers","slug":"this-paper-had-the-smartest-reviewers","title":"This Paper Had the Smartest Reviewers -- Flattery Detection Utilising an Audio-Textual Transformer-Based Approach","date":"2024-06-25","arxiv_id":"2406.17667","n_code_links":1,"syntology":null}],"record_sha256":"9f8cbebf314a541790e750cb9afc1055026f56bae4b966f7c92c84378a8bb1aa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}