{"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":"/task/hallucination/papers/11","list_of":"/task/hallucination","task":"Hallucination","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":11,"pages_in_order":19,"rows_per_page":100,"rows":[1001,1100],"of":1816,"counts":{"archive_papers_tagged":1816,"with_a_code_link":752,"where_syntology_ran_a_sample":276,"not_listed_spam_title":0,"listed":1816,"listed_where_code_ran":276,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":240,"every_run_a_failure_of_syntologys_instrument":36,"listed_with_a_run_with_no_instrument_failure":240,"listed_every_run_a_failure_of_syntologys_instrument":36,"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":"/task/hallucination","prev":"/task/hallucination/papers/10","next":"/task/hallucination/papers/12","papers":[{"url":null,"slug":"medhallu-a-comprehensive-benchmark-for","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","date":"2025-02-20","arxiv_id":"2502.14302","repositories_listed":0,"syntology":null},{"url":null,"slug":"verify-when-uncertain-beyond-self-consistency","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","date":"2025-02-20","arxiv_id":"2502.15845","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-llm-fact-conflicting-hallucinations","title":"Detecting LLM Fact-conflicting Hallucinations Enhanced by Temporal-logic-based Reasoning","date":"2025-02-19","arxiv_id":"2502.13416","repositories_listed":0,"syntology":null},{"url":null,"slug":"opensearch-sql-enhancing-text-to-sql-with","title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","date":"2025-02-19","arxiv_id":"2502.14913","repositories_listed":0,"syntology":null},{"url":null,"slug":"refind-retrieval-augmented-factuality","title":"REFIND: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models","date":"2025-02-19","arxiv_id":"2502.13622","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-are-models-thinking-about-understanding","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","date":"2025-02-19","arxiv_id":"2502.13490","repositories_listed":0,"syntology":null},{"url":null,"slug":"cutpaste-find-efficient-multimodal","title":"CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base","date":"2025-02-18","arxiv_id":"2502.12591","repositories_listed":0,"syntology":null},{"url":null,"slug":"lost-in-transcription-found-in-distribution","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","date":"2025-02-18","arxiv_id":"2502.12414","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-your-uncertainty-scores-detect","title":"Can Your Uncertainty Scores Detect Hallucinated Entity?","date":"2025-02-17","arxiv_id":"2502.11948","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-llm-based-agents-in-medicine-how","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","date":"2025-02-16","arxiv_id":"2502.11211","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoothing-out-hallucinations-mitigating-llm","title":"Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation","date":"2025-02-16","arxiv_id":"2502.11306","repositories_listed":0,"syntology":null},{"url":null,"slug":"valuable-hallucinations-realizable-non","title":"Valuable Hallucinations: Realizable Non-realistic Propositions","date":"2025-02-16","arxiv_id":"2502.11113","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-rag-with-active-learning-on","title":"Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables","date":"2025-02-13","arxiv_id":"2502.09073","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepseek-on-a-trip-inducing-targeted-visual","title":"DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities","date":"2025-02-11","arxiv_id":"2502.07905","repositories_listed":0,"syntology":null},{"url":null,"slug":"refine-knowledge-of-large-language-models-via","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","date":"2025-02-11","arxiv_id":"2502.07184","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detection-a-probabilistic","title":"Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis","date":"2025-02-10","arxiv_id":"2502.08663","repositories_listed":0,"syntology":null},{"url":null,"slug":"challengeme-an-adversarial-learning-enabled","title":"ChallengeMe: An Adversarial Learning-enabled Text Summarization Framework","date":"2025-02-07","arxiv_id":"2502.05084","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-hallucination-detection-through-1","title":"Enhancing Hallucination Detection through Noise Injection","date":"2025-02-06","arxiv_id":"2502.03799","repositories_listed":0,"syntology":null},{"url":null,"slug":"truthflow-truthful-llm-generation-via","title":"TruthFlow: Truthful LLM Generation via Representation Flow Correction","date":"2025-02-06","arxiv_id":"2502.04556","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-schema-guided-reason-while-retrieve","title":"A Schema-Guided Reason-while-Retrieve framework for Reasoning on Scene Graphs with Large-Language-Models (LLMs)","date":"2025-02-05","arxiv_id":"2502.03450","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-object-hallucinations-in-large-1","title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration","date":"2025-02-04","arxiv_id":"2502.01969","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-use-of-diffusion-models-for","title":"Assessing the use of Diffusion models for motion artifact correction in brain MRI","date":"2025-02-03","arxiv_id":"2502.01418","repositories_listed":0,"syntology":null},{"url":null,"slug":"eliciting-language-model-behaviors-with","title":"Eliciting Language Model Behaviors with Investigator Agents","date":"2025-02-03","arxiv_id":"2502.01236","repositories_listed":0,"syntology":null},{"url":null,"slug":"mj-video-fine-grained-benchmarking-and","title":"MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation","date":"2025-02-03","arxiv_id":"2502.01719","repositories_listed":0,"syntology":null},{"url":null,"slug":"selfcheckagent-zero-resource-hallucination","title":"SelfCheckAgent: Zero-Resource Hallucination Detection in Generative Large Language Models","date":"2025-02-03","arxiv_id":"2502.01812","repositories_listed":0,"syntology":null},{"url":null,"slug":"mint-mitigating-hallucinations-in-large","title":"MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction","date":"2025-02-02","arxiv_id":"2502.00717","repositories_listed":0,"syntology":null},{"url":null,"slug":"importing-phantoms-measuring-llm-package","title":"Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities","date":"2025-01-31","arxiv_id":"2501.19012","repositories_listed":0,"syntology":null},{"url":null,"slug":"poison-as-cure-visual-noise-for-mitigating","title":"Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs","date":"2025-01-31","arxiv_id":"2501.19164","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-optimized-framework-for","title":"Few-Shot Optimized Framework for Hallucination Detection in Resource-Limited NLP Systems","date":"2025-01-28","arxiv_id":"2501.16616","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinated-translations-in-large","title":"Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization","date":"2025-01-28","arxiv_id":"2501.17295","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-source-retrieval-augmented-generation","title":"Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers","date":"2025-01-28","arxiv_id":"2502.15722","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-large-vision-language-models-for","title":"Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis","date":"2025-01-26","arxiv_id":"2501.15370","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-hallucination-in-large-vision","title":"Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities","date":"2025-01-25","arxiv_id":"2501.15046","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirage-in-the-eyes-hallucination-attack-on","title":"Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink","date":"2025-01-25","arxiv_id":"2501.15269","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-and-mitigating-hallucinations-in","title":"Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensing","date":"2025-01-24","arxiv_id":"2501.14905","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-modeling-and-question-answering","title":"Comprehensive Modeling and Question Answering of Cancer Clinical Practice Guidelines using LLMs","date":"2025-01-23","arxiv_id":"2501.13984","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucinations-can-improve-large-language","title":"Hallucinations Can Improve Large Language Models in Drug Discovery","date":"2025-01-23","arxiv_id":"2501.13824","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-reward-optimizing-rag-with-reward","title":"RAG-Reward: Optimizing RAG with Reward Modeling and RLHF","date":"2025-01-22","arxiv_id":"2501.13264","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-to-question-retrieval-for","title":"Question-to-Question Retrieval for Hallucination-Free Knowledge Access: An Approach for Wikipedia and Wikidata Question Answering","date":"2025-01-20","arxiv_id":"2501.11301","repositories_listed":0,"syntology":null},{"url":null,"slug":"arxeval-evaluating-retrieval-and-generation","title":"ArxEval: Evaluating Retrieval and Generation in Language Models for Scientific Literature","date":"2025-01-17","arxiv_id":"2501.10483","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-guided-self-reflection-for-zero","title":"Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models","date":"2025-01-17","arxiv_id":"2501.09997","repositories_listed":0,"syntology":null},{"url":null,"slug":"frag-a-flexible-modular-framework-for","title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs","date":"2025-01-17","arxiv_id":"2501.09957","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-responsible-llms-inherent-risk","title":"A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy","date":"2025-01-16","arxiv_id":"2501.09431","repositories_listed":0,"syntology":null},{"url":null,"slug":"halogen-fantastic-llm-hallucinations-and","title":"HALoGEN: Fantastic LLM Hallucinations and Where to Find Them","date":"2025-01-14","arxiv_id":"2501.08292","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt-as-a-monte-carlo-language-tree-a","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","date":"2025-01-13","arxiv_id":"2501.07641","repositories_listed":0,"syntology":null},{"url":null,"slug":"medct-a-clinical-terminology-graph-for","title":"MedCT: A Clinical Terminology Graph for Generative AI Applications in Healthcare","date":"2025-01-11","arxiv_id":"2501.06465","repositories_listed":0,"syntology":null},{"url":null,"slug":"hermit-kingdom-through-the-lens-of-multiple","title":"Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea","date":"2025-01-10","arxiv_id":"2501.05981","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-with-partial-certainty-conformal","title":"Seeing with Partial Certainty: Conformal Prediction for Robotic Scene Recognition in Built Environments","date":"2025-01-09","arxiv_id":"2501.04947","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervision-free-vision-language-alignment","title":"Feedback-Driven Vision-Language Alignment with Minimal Human Supervision","date":"2025-01-08","arxiv_id":"2501.04568","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-check-evaluating-multimodal-retrieval","title":"RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance","date":"2025-01-07","arxiv_id":"2501.03995","repositories_listed":0,"syntology":null},{"url":null,"slug":"eagle-enhanced-visual-grounding-minimizes","title":"EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models","date":"2025-01-06","arxiv_id":"2501.02699","repositories_listed":0,"syntology":null},{"url":null,"slug":"flipedrag-black-box-opinion-manipulation","title":"FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models","date":"2025-01-06","arxiv_id":"2501.02968","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundations-of-genir","title":"Foundations of GenIR","date":"2025-01-06","arxiv_id":"2501.02842","repositories_listed":0,"syntology":null},{"url":null,"slug":"carbonchat-large-language-model-based","title":"CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System","date":"2025-01-03","arxiv_id":"2501.02031","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-legal-aid-understanding-legal-needs","title":"LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries","date":"2025-01-03","arxiv_id":"2501.01711","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-uncertainty-modeling-with-semantic","title":"Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection","date":"2025-01-02","arxiv_id":"2501.02020","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enhanced-symbolic","title":"Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion","date":"2025-01-02","arxiv_id":"2501.01246","repositories_listed":0,"syntology":null},{"url":null,"slug":"illusionbench-a-large-scale-and-comprehensive","title":"IllusionBench: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models","date":"2025-01-01","arxiv_id":"2501.00848","repositories_listed":0,"syntology":null},{"url":null,"slug":"popen-preference-based-optimization-and","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"stop-learning-it-all-to-mitigate-visual","title":"Stop Learning it all to Mitigate Visual Hallucination, Focus on the Hallucination Target.","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-rewardbench-a-challenging-benchmark-for","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-faithfulness-metrics-for","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","date":"2024-12-31","arxiv_id":"2501.00269","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-desired-comments-for-enhanced-code","title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","date":"2024-12-29","arxiv_id":"2412.20340","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-text-to-image-model-robust-to-caption","title":"Is Your Text-to-Image Model Robust to Caption Noise?","date":"2024-12-27","arxiv_id":"2412.19531","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-depth-based-pipeline-for-selfie","title":"An End-to-End Depth-Based Pipeline for Selfie Image Rectification","date":"2024-12-26","arxiv_id":"2412.19189","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhallbench-a-new-benchmark-for-assessing","title":"MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models","date":"2024-12-25","arxiv_id":"2412.18947","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-hallucinations-to-facts-enhancing","title":"From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs","date":"2024-12-24","arxiv_id":"2412.18672","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-factuality-with-explicit-working","title":"Improving Factuality with Explicit Working Memory","date":"2024-12-24","arxiv_id":"2412.18069","repositories_listed":0,"syntology":null},{"url":null,"slug":"alzheimerrag-multimodal-retrieval-augmented","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for PubMed articles","date":"2024-12-21","arxiv_id":"2412.16701","repositories_listed":0,"syntology":null},{"url":null,"slug":"logical-consistency-of-large-language-models","title":"Logical Consistency of Large Language Models in Fact-checking","date":"2024-12-20","arxiv_id":"2412.16100","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-robust-hyper-detailed-image-captioning","title":"Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage","date":"2024-12-20","arxiv_id":"2412.15484","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-dspy-teleprompter","title":"A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation","date":"2024-12-19","arxiv_id":"2412.15298","repositories_listed":0,"syntology":null},{"url":null,"slug":"dehallucinating-parallel-context-extension","title":"Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation","date":"2024-12-19","arxiv_id":"2412.14905","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-pipeline-optimization-for-cancer","title":"Query pipeline optimization for cancer patient question answering systems","date":"2024-12-19","arxiv_id":"2412.14751","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-cite-improving-attributed-text","title":"Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling","date":"2024-12-19","arxiv_id":"2412.14860","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-preference-optimization-with-self","title":"Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation","date":"2024-12-19","arxiv_id":"2412.14487","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-llms-good-literature-review-writers","title":"Are LLMs Good Literature Review Writers? Evaluating the Literature Review Writing Ability of Large Language Models","date":"2024-12-18","arxiv_id":"2412.13612","repositories_listed":0,"syntology":null},{"url":null,"slug":"cracking-the-code-of-hallucination-in-lvlms","title":"Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence","date":"2024-12-18","arxiv_id":"2412.13949","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mapreduce-approach-to-effectively-utilize","title":"A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models","date":"2024-12-17","arxiv_id":"2412.15271","repositories_listed":0,"syntology":null},{"url":null,"slug":"rextrust-a-model-for-fine-grained","title":"ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports","date":"2024-12-17","arxiv_id":"2412.15264","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-external-knowledge-is-preferred-by-llms","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context","date":"2024-12-17","arxiv_id":"2412.12632","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-to-speak-when-to-abstain-contrastive","title":"When to Speak, When to Abstain: Contrastive Decoding with Abstention","date":"2024-12-17","arxiv_id":"2412.12527","repositories_listed":0,"syntology":null},{"url":null,"slug":"cg-bench-clue-grounded-question-answering","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","date":"2024-12-16","arxiv_id":"2412.12075","repositories_listed":0,"syntology":null},{"url":null,"slug":"combating-multimodal-llm-hallucination-via","title":"Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning","date":"2024-12-15","arxiv_id":"2412.11124","repositories_listed":0,"syntology":null},{"url":null,"slug":"rac3-retrieval-augmented-corner-case","title":"RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models","date":"2024-12-15","arxiv_id":"2412.11050","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-dialog-systems-for-the","title":"Task-Oriented Dialog Systems for the Senegalese Wolof Language","date":"2024-12-15","arxiv_id":"2412.11203","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-retrieval-augmented-generation","title":"Accelerating Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.15246","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisyeqa-benchmarking-embodied-question","title":"NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries","date":"2024-12-14","arxiv_id":"2412.10726","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinking-with-knowledge-graphs-enhancing-llm","title":"Thinking with Knowledge Graphs: Enhancing LLM Reasoning Through Structured Data","date":"2024-12-14","arxiv_id":"2412.10654","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-models-for-4","title":"Benchmarking large language models for materials synthesis: the case of atomic layer deposition","date":"2024-12-13","arxiv_id":"2412.10477","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-llm-hallucination-through-layer","title":"Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Unanswerable Questions and Ambiguous Prompts","date":"2024-12-13","arxiv_id":"2412.10246","repositories_listed":0,"syntology":null},{"url":null,"slug":"tacomore-leveraging-the-potential-of-llms-in","title":"TACOMORE: Leveraging the Potential of LLMs in Corpus-based Discourse Analysis with Prompt Engineering","date":"2024-12-13","arxiv_id":"2412.10139","repositories_listed":0,"syntology":null},{"url":"/paper/multi-task-learning-with-llms-for-implicit","slug":"multi-task-learning-with-llms-for-implicit","title":"Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning","date":"2024-12-12","arxiv_id":"2412.09046","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucana-fixing-llm-hallucination-with-a","title":"HalluCana: Fixing LLM Hallucination with A Canary Lookahead","date":"2024-12-10","arxiv_id":"2412.07965","repositories_listed":0,"syntology":null},{"url":null,"slug":"methods-for-legal-citation-prediction-in-the","title":"Methods for Legal Citation Prediction in the Age of LLMs: An Australian Law Case Study","date":"2024-12-09","arxiv_id":"2412.06272","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-hallucination-in-text-to-image","title":"Evaluating Hallucination in Text-to-Image Diffusion Models with Scene-Graph based Question-Answering Agent","date":"2024-12-07","arxiv_id":"2412.05722","repositories_listed":0,"syntology":null},{"url":null,"slug":"100-hallucination-elimination-using-acurai","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","date":"2024-12-06","arxiv_id":"2412.05223","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-approach-for-conversational-ai","title":"TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG","date":"2024-12-06","arxiv_id":"2412.05447","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-align-utilizing-large-language-models-for","title":"LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs","date":"2024-12-06","arxiv_id":"2412.04690","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-alignment-of-large-language","title":"Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization","date":"2024-12-06","arxiv_id":"2412.05469","repositories_listed":0,"syntology":null}],"record_sha256":"87d60a3e9ac99e2e2e80ee7c5bf1c8ac7835c1a654a473c36404f4eaee942e77","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}