{"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/16","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":16,"pages_in_order":109,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/method/attention-dropout/papers/17","papers":[{"paper":null,"slug":"babylm-challenge-exploring-the-effect-of","title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency","date":"2024-11-14","arxiv_id":"2411.09587","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-static-tools-evaluating-large-language","title":"Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection","date":"2024-11-14","arxiv_id":"2411.09772","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-and-practical-evaluation-of","title":"Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering","date":"2024-11-14","arxiv_id":"2411.09213","n_code_links":0,"syntology":null},{"paper":null,"slug":"hategpt-unleashing-gpt-3-5-turbo-to-combat","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","date":"2024-11-14","arxiv_id":"2411.09214","n_code_links":0,"syntology":null},{"paper":"/paper/initial-nugget-evaluation-results-for-the","slug":"initial-nugget-evaluation-results-for-the","title":"Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework","date":"2024-11-14","arxiv_id":"2411.09607","n_code_links":2,"syntology":null},{"paper":"/paper/a-large-scale-study-of-relevance-assessments","slug":"a-large-scale-study-of-relevance-assessments","title":"A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look","date":"2024-11-13","arxiv_id":"2411.08275","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyst-reports-and-stock-performance","title":"Analyst Reports and Stock Performance: Evidence from the Chinese Market","date":"2024-11-13","arxiv_id":"2411.08726","n_code_links":0,"syntology":null},{"paper":null,"slug":"camembert-2-0-a-smarter-french-language-model","title":"CamemBERT 2.0: A Smarter French Language Model Aged to Perfection","date":"2024-11-13","arxiv_id":"2411.08868","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmstinger-jailbreaking-llms-using-rl-fine","title":"LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs","date":"2024-11-13","arxiv_id":"2411.08862","n_code_links":0,"syntology":null},{"paper":"/paper/logllm-log-based-anomaly-detection-using","slug":"logllm-log-based-anomaly-detection-using","title":"LogLLM: Log-based Anomaly Detection Using Large Language Models","date":"2024-11-13","arxiv_id":"2411.08561","n_code_links":1,"syntology":null},{"paper":null,"slug":"responsible-ai-in-construction-safety","title":"Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering","date":"2024-11-13","arxiv_id":"2411.08320","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-optimizing-a-retrieval-augmented","title":"Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data","date":"2024-11-13","arxiv_id":"2411.08438","n_code_links":0,"syntology":null},{"paper":null,"slug":"valtest-automated-validation-of-language","title":"VALTEST: Automated Validation of Language Model Generated Test Cases","date":"2024-11-13","arxiv_id":"2411.08254","n_code_links":0,"syntology":null},{"paper":"/paper/controlled-evaluation-of-syntactic-knowledge","slug":"controlled-evaluation-of-syntactic-knowledge","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","date":"2024-11-12","arxiv_id":"2411.07474","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-chatgpt-3-5-efficiency-in-solving","slug":"evaluating-chatgpt-3-5-efficiency-in-solving","title":"Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis","date":"2024-11-12","arxiv_id":"2411.07529","n_code_links":1,"syntology":null},{"paper":"/paper/fair-summarization-bridging-quality-and","slug":"fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","date":"2024-11-12","arxiv_id":"2411.07521","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":["PortNLP/FairEXTSummarizer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"leveraging-multimodal-models-for-enhanced","title":"Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's Disease","date":"2024-11-12","arxiv_id":"2411.07871","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-app-squatting-and-cloning","title":"LLM App Squatting and Cloning","date":"2024-11-12","arxiv_id":"2411.07518","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-optimization-for-parametric-knowledge","title":"Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models","date":"2024-11-12","arxiv_id":"2411.07820","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-time-series-forecasting","slug":"retrieval-augmented-time-series-forecasting","title":"Retrieval Augmented Time Series Forecasting","date":"2024-11-12","arxiv_id":"2411.08249","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kutaytire/retrieval-augmented-time-series-forecasting"],"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":"trustful-llms-customizing-and-grounding-text","title":"Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders","date":"2024-11-12","arxiv_id":"2411.07870","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-multi-task-learning-architecture","title":"A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information","date":"2024-11-11","arxiv_id":"2411.06855","n_code_links":0,"syntology":null},{"paper":null,"slug":"ambient-ai-scribing-support-comparing-the","title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","date":"2024-11-11","arxiv_id":"2411.06713","n_code_links":0,"syntology":null},{"paper":"/paper/assistrag-boosting-the-potential-of-large","slug":"assistrag-boosting-the-potential-of-large","title":"AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant","date":"2024-11-11","arxiv_id":"2411.06805","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":8,"n_instrument":2,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["smallporridge/assistrag"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/autonomous-droplet-microfluidic-design","slug":"autonomous-droplet-microfluidic-design","title":"Autonomous Droplet Microfluidic Design Framework with Large Language Models","date":"2024-11-11","arxiv_id":"2411.06691","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancer-answer-empowering-cancer-care-with","title":"Cancer-Answer: Empowering Cancer Care with Advanced Large Language Models","date":"2024-11-11","arxiv_id":"2411.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-on-financial","title":"Evaluating Large Language Models on Financial Report Summarization: An Empirical Study","date":"2024-11-11","arxiv_id":"2411.06852","n_code_links":0,"syntology":null},{"paper":null,"slug":"explore-the-reasoning-capability-of-llms-in","title":"Explore the Reasoning Capability of LLMs in the Chess Testbed","date":"2024-11-11","arxiv_id":"2411.06655","n_code_links":0,"syntology":null},{"paper":null,"slug":"invar-rag-invariant-llm-aligned-retrieval-for","title":"Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation","date":"2024-11-11","arxiv_id":"2411.07021","n_code_links":0,"syntology":null},{"paper":null,"slug":"la4sr-illuminating-the-dark-proteome-with","title":"LA4SR: illuminating the dark proteome with generative AI","date":"2024-11-11","arxiv_id":"2411.06798","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-active-privacy-auditing-in-supervised-fine","title":"On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models","date":"2024-11-11","arxiv_id":"2411.07070","n_code_links":0,"syntology":null},{"paper":null,"slug":"spartan-a-sparse-transformer-learning-local","title":"SPARTAN: A Sparse Transformer Learning Local Causation","date":"2024-11-11","arxiv_id":"2411.06890","n_code_links":0,"syntology":null},{"paper":null,"slug":"tempcharbert-keystroke-dynamics-for","title":"TempCharBERT: Keystroke Dynamics for Continuous Access Control Based on Pre-trained Language Models","date":"2024-11-11","arxiv_id":"2411.07224","n_code_links":0,"syntology":null},{"paper":null,"slug":"token2wave","title":"The Backpropagation of the Wave Network","date":"2024-11-11","arxiv_id":"2411.06989","n_code_links":0,"syntology":null},{"paper":"/paper/toward-optimal-search-and-retrieval-for-rag","slug":"toward-optimal-search-and-retrieval-for-rag","title":"Toward Optimal Search and Retrieval for RAG","date":"2024-11-11","arxiv_id":"2411.07396","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-efficient-fine-tuning-for-gpt-like","title":"Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques","date":"2024-11-10","arxiv_id":"2411.06445","n_code_links":0,"syntology":null},{"paper":"/paper/region-aware-text-to-image-generation-via","slug":"region-aware-text-to-image-generation-via","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","date":"2024-11-10","arxiv_id":"2411.06558","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nju-pcalab/rag-diffusion"],"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","unlocated"]}}},{"paper":null,"slug":"clustering-algorithms-and-rag-enhancing-semi","title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","date":"2024-11-09","arxiv_id":"2411.06175","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-reference-errors-in-scientific","slug":"detecting-reference-errors-in-scientific","title":"Detecting Reference Errors in Scientific Literature with Large Language Models","date":"2024-11-09","arxiv_id":"2411.06101","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-knowledge-boundaries-in-large","title":"Exploring Knowledge Boundaries in Large Language Models for Retrieval Judgment","date":"2024-11-09","arxiv_id":"2411.06207","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-intent-classification-based-on","title":"Improved intent classification based on context information using a windows-based approach","date":"2024-11-09","arxiv_id":"2411.06022","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-retrieval-augmented-generation-for-1","title":"Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrieval","date":"2024-11-09","arxiv_id":"2411.06237","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-detection-of-llm-generated-text-a","title":"Robust Detection of LLM-Generated Text: A Comparative Analysis","date":"2024-11-09","arxiv_id":"2411.06248","n_code_links":0,"syntology":null},{"paper":null,"slug":"sufficient-context-a-new-lens-on-retrieval","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","date":"2024-11-09","arxiv_id":"2411.06037","n_code_links":0,"syntology":null},{"paper":"/paper/a-taxonomy-of-agentops-for-enabling","slug":"a-taxonomy-of-agentops-for-enabling","title":"AgentOps: Enabling Observability of LLM Agents","date":"2024-11-08","arxiv_id":"2411.05285","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-visual-classification-using","slug":"enhancing-visual-classification-using","title":"Enhancing Visual Classification using Comparative Descriptors","date":"2024-11-08","arxiv_id":"2411.05357","n_code_links":1,"syntology":null},{"paper":"/paper/findver-explainable-claim-verification-over","slug":"findver-explainable-claim-verification-over","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","date":"2024-11-08","arxiv_id":"2411.05764","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-semantic-cache-reducing-llm-costs-and","title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching","date":"2024-11-08","arxiv_id":"2411.05276","n_code_links":0,"syntology":null},{"paper":"/paper/heartbert-a-self-supervised-ecg-embedding","slug":"heartbert-a-self-supervised-ecg-embedding","title":"HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis","date":"2024-11-08","arxiv_id":"2411.11896","n_code_links":1,"syntology":null},{"paper":"/paper/intellbot-retrieval-augmented-llm-chatbot-for","slug":"intellbot-retrieval-augmented-llm-chatbot-for","title":"IntellBot: Retrieval Augmented LLM Chatbot for Cyber Threat Knowledge Delivery","date":"2024-11-08","arxiv_id":"2411.05442","n_code_links":1,"syntology":null},{"paper":"/paper/learning-the-rules-of-peptide-self-assembly","slug":"learning-the-rules-of-peptide-self-assembly","title":"Learning the rules of peptide self-assembly through data mining with large language models","date":"2024-11-08","arxiv_id":"2411.05421","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-document-financial-question-answering","title":"Multi-Document Financial Question Answering using LLMs","date":"2024-11-08","arxiv_id":"2411.07264","n_code_links":0,"syntology":null},{"paper":null,"slug":"neko-toward-post-recognition-generative","title":"NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts","date":"2024-11-08","arxiv_id":"2411.05945","n_code_links":0,"syntology":null},{"paper":null,"slug":"qwen2-5-32b-leveraging-self-consistent-tool","title":"Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem Solving","date":"2024-11-08","arxiv_id":"2411.05934","n_code_links":0,"syntology":null},{"paper":"/paper/sentiment-analysis-of-cyberbullying-data-in","slug":"sentiment-analysis-of-cyberbullying-data-in","title":"Sentiment Analysis of Cyberbullying Data in Social Media","date":"2024-11-08","arxiv_id":"2411.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-robustness-of-in-context-learning","title":"Adversarial Robustness of In-Context Learning in Transformers for Linear Regression","date":"2024-11-07","arxiv_id":"2411.05189","n_code_links":0,"syntology":null},{"paper":null,"slug":"best-practices-for-distilling-large-language","title":"Best Practices for Distilling Large Language Models into BERT for Web Search Ranking","date":"2024-11-07","arxiv_id":"2411.04539","n_code_links":0,"syntology":null},{"paper":"/paper/deploying-large-language-models-with","slug":"deploying-large-language-models-with","title":"Deploying Large Language Models With Retrieval Augmented Generation","date":"2024-11-07","arxiv_id":"2411.11895","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-classroom-teaching-with-llms-and","title":"Enhancing classroom teaching with LLMs and RAG","date":"2024-11-07","arxiv_id":"2411.04341","n_code_links":0,"syntology":null},{"paper":"/paper/finetunebench-how-well-do-commercial-fine","slug":"finetunebench-how-well-do-commercial-fine","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","date":"2024-11-07","arxiv_id":"2411.05059","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-guided-monte-carlo-tree-search-for","title":"GPT-Guided Monte Carlo Tree Search for Symbolic Regression in Financial Fraud Detection","date":"2024-11-07","arxiv_id":"2411.04459","n_code_links":0,"syntology":null},{"paper":null,"slug":"m3docrag-multi-modal-retrieval-is-what-you","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","date":"2024-11-07","arxiv_id":"2411.04952","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrievegpt-merging-prompts-and-mathematical","title":"RetrieveGPT: Merging Prompts and Mathematical Models for Enhanced Code-Mixed Information Retrieval","date":"2024-11-07","arxiv_id":"2411.04752","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-between-bert-and-gpt-for-text","title":"Selecting Between BERT and GPT for Text Classification in Political Science Research","date":"2024-11-07","arxiv_id":"2411.05050","n_code_links":0,"syntology":null},{"paper":null,"slug":"stand-guard-a-small-task-adaptive-content","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","date":"2024-11-07","arxiv_id":"2411.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"words-that-move-markets-quantifying-the","title":"Words that Move Markets- Quantifying the Impact of RBI's Monetary Policy Communications on Indian Financial Market","date":"2024-11-07","arxiv_id":"2411.04808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multilingual-sentiment-lexicon-for-low","title":"A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI","date":"2024-11-06","arxiv_id":"2411.04316","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-rag-models-with-graph-structures","title":"Advanced RAG Models with Graph Structures: Optimizing Complex Knowledge Reasoning and Text Generation","date":"2024-11-06","arxiv_id":"2411.03572","n_code_links":0,"syntology":null},{"paper":"/paper/can-custom-models-learn-in-context-an","slug":"can-custom-models-learn-in-context-an","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","date":"2024-11-06","arxiv_id":"2411.03945","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-guidance-for-retrievers","title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","date":"2024-11-06","arxiv_id":"2411.03957","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-word-vectors-to-multimodal-embeddings","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","date":"2024-11-06","arxiv_id":"2411.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-device-emoji-classifier-trained-with-gpt","title":"On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard","date":"2024-11-06","arxiv_id":"2411.05031","n_code_links":0,"syntology":null},{"paper":null,"slug":"phdgpt-introducing-a-psychometric-and","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","date":"2024-11-06","arxiv_id":"2411.10473","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragulator-lightweight-out-of-context","title":"RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation","date":"2024-11-06","arxiv_id":"2411.03920","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpreting-language-models-a-case","slug":"towards-interpreting-language-models-a-case","title":"Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning","date":"2024-11-06","arxiv_id":"2411.05037","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":["msakarvadia/attentionlens"],"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/understanding-the-effects-of-human-written","slug":"understanding-the-effects-of-human-written","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","date":"2024-11-06","arxiv_id":"2411.03806","n_code_links":1,"syntology":null},{"paper":null,"slug":"youtube-comments-decoded-leveraging-llms-for","title":"YouTube Comments Decoded: Leveraging LLMs for Low Resource Language Classification","date":"2024-11-06","arxiv_id":"2411.05039","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transformer-training-efficiency","title":"Enhancing Transformer Training Efficiency with Dynamic Dropout","date":"2024-11-05","arxiv_id":"2411.03236","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":"/paper/htmlrag-html-is-better-than-plain-text-for","slug":"htmlrag-html-is-better-than-plain-text-for","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","date":"2024-11-05","arxiv_id":"2411.02959","n_code_links":1,"syntology":null},{"paper":null,"slug":"laser-attention-with-exponential","title":"LASER: Attention with Exponential Transformation","date":"2024-11-05","arxiv_id":"2411.03493","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-rag-performance-of-large","title":"Long Context RAG Performance of Large Language Models","date":"2024-11-05","arxiv_id":"2411.03538","n_code_links":0,"syntology":null},{"paper":null,"slug":"persianrag-a-retrieval-augmented-generation","title":"PersianRAG: A Retrieval-Augmented Generation System for Persian Language","date":"2024-11-05","arxiv_id":"2411.02832","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-analysis-of-counterfactual","title":"A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers","date":"2024-11-04","arxiv_id":"2411.02643","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-limitations-of-llms-in","title":"Advancements and limitations of LLMs in replicating human color-word associations","date":"2024-11-04","arxiv_id":"2411.02116","n_code_links":0,"syntology":null},{"paper":"/paper/ask-and-it-shall-be-given-turing-completeness","slug":"ask-and-it-shall-be-given-turing-completeness","title":"Ask, and it shall be given: On the Turing completeness of prompting","date":"2024-11-04","arxiv_id":"2411.01992","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-language-models-enable-in-context","title":"Can Language Models Enable In-Context Database?","date":"2024-11-04","arxiv_id":"2411.01807","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-ability-of-large-language-1","title":"Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast","date":"2024-11-04","arxiv_id":"2411.02318","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-emotional-descriptions-to","title":"Grounding Emotional Descriptions to Electrovibration Haptic Signals","date":"2024-11-04","arxiv_id":"2411.02118","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdeval-massively-multilingual-code-debugging","title":"MdEval: Massively Multilingual Code Debugging","date":"2024-11-04","arxiv_id":"2411.02310","n_code_links":0,"syntology":null},{"paper":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","n_code_links":1,"syntology":null},{"paper":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","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 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":["tum-ai/number-token-loss"],"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/teleoracle-fine-tuned-retrieval-augmented","slug":"teleoracle-fine-tuned-retrieval-augmented","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","date":"2024-11-04","arxiv_id":"2411.02617","n_code_links":1,"syntology":null},{"paper":"/paper/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"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","unlocated"]}}},{"paper":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-extraction-attacks-in-retrieval","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","date":"2024-11-03","arxiv_id":"2411.01705","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","n_code_links":0,"syntology":null}],"record_sha256":"78a2c9690c69ca768208268a4995439b73bbc13246239e5ce0abc3f301d07d7d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}