{"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/9","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":9,"pages_in_order":19,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/hallucination/papers/10","papers":[{"url":null,"slug":"reinforcement-learning-for-better-verbalized","title":"Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation","date":"2025-05-29","arxiv_id":"2505.23912","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-hallucination-in-multi-round","title":"Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks","date":"2025-05-28","arxiv_id":"2505.23843","repositories_listed":0,"syntology":null},{"url":null,"slug":"skewroute-training-free-llm-routing-for","title":"SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context","date":"2025-05-28","arxiv_id":"2505.23841","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lightweight-multi-expert-generative","title":"A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction","date":"2025-05-27","arxiv_id":"2505.21109","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-large-vision","title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","date":"2025-05-27","arxiv_id":"2505.21472","repositories_listed":0,"syntology":null},{"url":"/paper/attention-you-vision-language-model-could-be","slug":"attention-you-vision-language-model-could-be","title":"Attention! You Vision Language Model Could Be Maliciously Manipulated","date":"2025-05-26","arxiv_id":"2505.19911","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attention-you-vision-language-model-could-be#ran","syntology_url":"https://syntology.ai/paper/2505.19911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19911"}},"official":null}},{"url":null,"slug":"enhancing-visual-reliance-in-text-generation","title":"Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models","date":"2025-05-26","arxiv_id":"2505.19498","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-with-vision-a-conditional","title":"Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs","date":"2025-05-26","arxiv_id":"2505.19678","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-attention-heads-efficient","title":"Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs","date":"2025-05-26","arxiv_id":"2505.20045","repositories_listed":0,"syntology":null},{"url":null,"slug":"guardian-safeguarding-llm-multi-agent","title":"GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling","date":"2025-05-25","arxiv_id":"2505.19234","repositories_listed":0,"syntology":null},{"url":null,"slug":"lllms-a-data-driven-survey-of-evolving","title":"LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models","date":"2025-05-25","arxiv_id":"2505.19240","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-thinking-less-seeing-assessing-amplified","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","date":"2025-05-23","arxiv_id":"2505.21523","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-with-lies-curriculum-dpo-on","title":"Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection","date":"2025-05-23","arxiv_id":"2505.17558","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-thought-poisoning-attacks-against-r1","title":"Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems","date":"2025-05-22","arxiv_id":"2505.16367","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-powered-agents-for-navigating-venice-s","title":"LLM-Powered Agents for Navigating Venice's Historical Cadastre","date":"2025-05-22","arxiv_id":"2505.17148","repositories_listed":0,"syntology":null},{"url":null,"slug":"locate-then-merge-neuron-level-parameter","title":"Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs","date":"2025-05-22","arxiv_id":"2505.16703","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-far-and-clearly-mitigating","title":"Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding","date":"2025-05-22","arxiv_id":"2505.16652","repositories_listed":0,"syntology":null},{"url":null,"slug":"shadows-in-the-attention-contextual","title":"Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs","date":"2025-05-22","arxiv_id":"2505.16894","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-lvlms-via-sparse-autoencoder-for","title":"Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation","date":"2025-05-22","arxiv_id":"2505.16146","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncle-uncertainty-expressions-in-long-form","title":"UNCLE: Uncertainty Expressions in Long-Form Generation","date":"2025-05-22","arxiv_id":"2505.16922","repositories_listed":0,"syntology":null},{"url":null,"slug":"aug2search-enhancing-facebook-marketplace","title":"Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation","date":"2025-05-21","arxiv_id":"2505.16065","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucinate-at-the-last-in-long-response","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","date":"2025-05-21","arxiv_id":"2505.15291","repositories_listed":0,"syntology":null},{"url":null,"slug":"hcrmp-a-llm-hinted-contextual-reinforcement","title":"HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving","date":"2025-05-21","arxiv_id":"2505.15793","repositories_listed":0,"syntology":null},{"url":null,"slug":"kaft-knowledge-aware-fine-tuning-for-boosting","title":"KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance","date":"2025-05-21","arxiv_id":"2505.15480","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-prompting-for-improving-llm","title":"Multilingual Prompting for Improving LLM Generation Diversity","date":"2025-05-21","arxiv_id":"2505.15229","repositories_listed":0,"syntology":null},{"url":null,"slug":"next-eval-next-evaluation-of-traditional-and","title":"NEXT-EVAL: Next Evaluation of Traditional and LLM Web Data Record Extraction","date":"2025-05-21","arxiv_id":"2505.17125","repositories_listed":0,"syntology":null},{"url":null,"slug":"ovip-online-vision-language-preference","title":"OViP: Online Vision-Language Preference Learning","date":"2025-05-21","arxiv_id":"2505.15963","repositories_listed":0,"syntology":null},{"url":null,"slug":"reppl-recalibrating-perplexity-by-uncertainty","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","date":"2025-05-21","arxiv_id":"2505.15386","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-attention-distribution-to","title":"Aligning Attention Distribution to Information Flow for Hallucination Mitigation in Large Vision-Language Models","date":"2025-05-20","arxiv_id":"2505.14257","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundations-of-unknown-aware-machine-learning","title":"Foundations of Unknown-aware Machine Learning","date":"2025-05-20","arxiv_id":"2505.14933","repositories_listed":0,"syntology":null},{"url":null,"slug":"jarvis-a-multi-agent-code-assistant-for-high","title":"JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation","date":"2025-05-20","arxiv_id":"2505.14978","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-rule-induction-towards-generalizable","title":"Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents","date":"2025-05-20","arxiv_id":"2505.14104","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-rag-driven-anomaly-detection-and","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","date":"2025-05-20","arxiv_id":"2505.13828","repositories_listed":0,"syntology":null},{"url":"/paper/pierce-the-mists-greet-the-sky-decipher","slug":"pierce-the-mists-greet-the-sky-decipher","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","date":"2025-05-20","arxiv_id":"2505.14406","repositories_listed":0,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pierce-the-mists-greet-the-sky-decipher#ran","syntology_url":"https://syntology.ai/paper/2505.14406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14406"}},"official":null}},{"url":null,"slug":"plane-geometry-problem-solving-with-multi","title":"Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey","date":"2025-05-20","arxiv_id":"2505.14340","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcing-question-answering-agents-with","title":"Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization","date":"2025-05-20","arxiv_id":"2505.17086","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hallucination-tax-of-reinforcement","title":"The Hallucination Tax of Reinforcement Finetuning","date":"2025-05-20","arxiv_id":"2505.13988","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-omnidirectional-reasoning-with-360-r1","title":"Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method","date":"2025-05-20","arxiv_id":"2505.14197","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-instruction-bottleneck-tuning","title":"Visual Instruction Bottleneck Tuning","date":"2025-05-20","arxiv_id":"2505.13946","repositories_listed":0,"syntology":null},{"url":null,"slug":"calm-whisper-reduce-whisper-hallucination-on","title":"Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down","date":"2025-05-19","arxiv_id":"2505.12969","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-and-mitigation-of-hallucination-in","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","date":"2025-05-19","arxiv_id":"2505.12886","repositories_listed":0,"syntology":null},{"url":null,"slug":"granary-speech-recognition-and-translation","title":"Granary: Speech Recognition and Translation Dataset in 25 European Languages","date":"2025-05-19","arxiv_id":"2505.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-videollms-via","title":"Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering","date":"2025-05-19","arxiv_id":"2505.12826","repositories_listed":0,"syntology":null},{"url":null,"slug":"selective-code-generation-for-functional","title":"Selective Code Generation for Functional Guarantees","date":"2025-05-19","arxiv_id":"2505.13553","repositories_listed":0,"syntology":null},{"url":null,"slug":"tianyi-a-traditional-chinese-medicine-all","title":"Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice","date":"2025-05-19","arxiv_id":"2505.13156","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-auxiliary-tasks-improves-reference","title":"Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation","date":"2025-05-18","arxiv_id":"2505.12265","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-via-inter-layer","title":"Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models","date":"2025-05-18","arxiv_id":"2505.12343","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-tower-of-babel-revisited-multilingual","title":"The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models","date":"2025-05-18","arxiv_id":"2505.12287","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-multimodal-large-language-models-ready","title":"Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?","date":"2025-05-17","arxiv_id":"2505.11907","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccnu-at-semeval-2025-task-3-leveraging","title":"CCNU at SemEval-2025 Task 3: Leveraging Internal and External Knowledge of Large Language Models for Multilingual Hallucination Annotation","date":"2025-05-17","arxiv_id":"2505.11965","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverging-towards-hallucination-detection-of","title":"Diverging Towards Hallucination: Detection of Failures in Vision-Language Models via Multi-token Aggregation","date":"2025-05-16","arxiv_id":"2505.11741","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-evaluation-of-stem-education","title":"Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning","date":"2025-05-16","arxiv_id":"2505.17050","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-agents-vs-agentic-ai-a-conceptual-taxonomy","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","date":"2025-05-15","arxiv_id":"2505.10468","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-multi-agent-framework-for","title":"A Multimodal Multi-Agent Framework for Radiology Report Generation","date":"2025-05-14","arxiv_id":"2505.09787","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-black-box-interpretability-of-llms","title":"Beyond the Black Box: Interpretability of LLMs in Finance","date":"2025-05-14","arxiv_id":"2505.24650","repositories_listed":0,"syntology":null},{"url":null,"slug":"ornithologist-towards-trustworthy-reasoning","title":"Ornithologist: Towards Trustworthy \"Reasoning\" about Central Bank Communications","date":"2025-05-14","arxiv_id":"2505.09083","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-large-language-models-on-task","title":"The Impact of Large Language Models on Task Automation in Manufacturing Services","date":"2025-05-14","arxiv_id":"2505.10581","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-schema-aware-event-extraction-with","title":"Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation","date":"2025-05-13","arxiv_id":"2505.08690","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-reliability-of-llms-combining","title":"Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification","date":"2025-05-13","arxiv_id":"2505.09031","repositories_listed":0,"syntology":null},{"url":null,"slug":"critique-before-thinking-mitigating","title":"Critique Before Thinking: Mitigating Hallucination through Rationale-Augmented Instruction Tuning","date":"2025-05-12","arxiv_id":"2505.07172","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-cost-and-benefits-of-training-context","title":"On the Cost and Benefits of Training Context with Utterance or Full Conversation Training: A Comparative Stud","date":"2025-05-12","arxiv_id":"2505.07202","repositories_listed":0,"syntology":null},{"url":null,"slug":"seredeep-hallucination-detection-in-retrieval","title":"SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion","date":"2025-05-12","arxiv_id":"2505.07528","repositories_listed":0,"syntology":null},{"url":null,"slug":"trumorgpt-graph-based-retrieval-augmented","title":"TrumorGPT: Graph-Based Retrieval-Augmented Large Language Model for Fact-Checking","date":"2025-05-11","arxiv_id":"2505.07891","repositories_listed":0,"syntology":null},{"url":null,"slug":"osiris-a-lightweight-open-source","title":"Osiris: A Lightweight Open-Source Hallucination Detection System","date":"2025-05-07","arxiv_id":"2505.04844","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-zero-shot-learning-with","title":"Interpretable Zero-shot Learning with Infinite Class Concepts","date":"2025-05-06","arxiv_id":"2505.03361","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-image-captioning-hallucinations-in","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models","date":"2025-05-06","arxiv_id":"2505.03420","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graphs-for-enhancing-large-language","title":"Knowledge Graphs for Enhancing Large Language Models in Entity Disambiguation","date":"2025-05-05","arxiv_id":"2505.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-analysis-for-visual-object","title":"A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models","date":"2025-05-04","arxiv_id":"2505.01958","repositories_listed":0,"syntology":null},{"url":null,"slug":"seval-ex-a-statement-level-framework-for","title":"SEval-Ex: A Statement-Level Framework for Explainable Summarization Evaluation","date":"2025-05-04","arxiv_id":"2505.02235","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-parsing-of-engineering-drawings-for","title":"Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer","date":"2025-05-02","arxiv_id":"2505.01530","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agents-based-user-values-mining-for","title":"Multi-agents based User Values Mining for Recommendation","date":"2025-05-02","arxiv_id":"2505.00981","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallumix-a-task-agnostic-multi-domain","title":"HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection","date":"2025-05-01","arxiv_id":"2505.00506","repositories_listed":0,"syntology":null},{"url":null,"slug":"triggering-hallucinations-in-llms-a","title":"Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models","date":"2025-05-01","arxiv_id":"2505.00557","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-box-visual-prompt-engineering-for","title":"Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models","date":"2025-04-30","arxiv_id":"2504.21559","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-and-robust-3d-blind-harmonization","title":"Efficient and robust 3D blind harmonization for large domain gaps","date":"2025-04-30","arxiv_id":"2505.00133","repositories_listed":0,"syntology":null},{"url":null,"slug":"localizing-before-answering-a-hallucination","title":"Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs","date":"2025-04-30","arxiv_id":"2505.00744","repositories_listed":0,"syntology":null},{"url":null,"slug":"mac-tuning-llm-multi-compositional-problem","title":"MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness","date":"2025-04-30","arxiv_id":"2504.21773","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-detect-intrinsic-hallucinations-in","title":"Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?","date":"2025-04-29","arxiv_id":"2504.20699","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-by-code-generation-llms","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","date":"2025-04-29","arxiv_id":"2504.20799","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automated-reinforcement-learning-reward","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","date":"2025-04-28","arxiv_id":"2504.19480","repositories_listed":0,"syntology":null},{"url":null,"slug":"explanatory-summarization-with-discourse","title":"Explanatory Summarization with Discourse-Driven Planning","date":"2025-04-27","arxiv_id":"2504.19339","repositories_listed":0,"syntology":null},{"url":null,"slug":"validating-network-protocol-parsers-with","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","date":"2025-04-25","arxiv_id":"2504.18050","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-calibration-of-prediction-sets-in","title":"Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction","date":"2025-04-24","arxiv_id":"2504.17671","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-personalizing-quantum-computing","title":"Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach","date":"2025-04-24","arxiv_id":"2504.18603","repositories_listed":0,"syntology":null},{"url":null,"slug":"im-possibility-of-automated-hallucination","title":"(Im)possibility of Automated Hallucination Detection in Large Language Models","date":"2025-04-23","arxiv_id":"2504.17004","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dance-of-atoms-de-novo-protein-design","title":"The Dance of Atoms-De Novo Protein Design with Diffusion Model","date":"2025-04-23","arxiv_id":"2504.16479","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-in-context-retrieval-based-method","title":"Grounded in Context: Retrieval-Based Method for Hallucination Detection","date":"2025-04-22","arxiv_id":"2504.15771","repositories_listed":0,"syntology":null},{"url":null,"slug":"insights-from-verification-training-a-verilog","title":"Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback","date":"2025-04-22","arxiv_id":"2504.15804","repositories_listed":0,"syntology":null},{"url":null,"slug":"aixamine-llm-safety-and-security-simplified","title":"aiXamine: Simplified LLM Safety and Security","date":"2025-04-21","arxiv_id":"2504.14985","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyrag-integrating-polyviews-into-retrieval","title":"POLYRAG: Integrating Polyviews into Retrieval-Augmented Generation for Medical Applications","date":"2025-04-21","arxiv_id":"2504.14917","repositories_listed":0,"syntology":null},{"url":null,"slug":"resnetvllm-2-addressing-resnetvllm-s-multi","title":"ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations","date":"2025-04-20","arxiv_id":"2504.14429","repositories_listed":0,"syntology":null},{"url":null,"slug":"density-measures-for-language-generation","title":"Density Measures for Language Generation","date":"2025-04-19","arxiv_id":"2504.14370","repositories_listed":0,"syntology":null},{"url":null,"slug":"hydra-an-agentic-reasoning-approach-for","title":"Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models","date":"2025-04-19","arxiv_id":"2504.14395","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stage-retrieval-for-operational","title":"Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy","date":"2025-04-18","arxiv_id":"2504.14044","repositories_listed":0,"syntology":null},{"url":null,"slug":"aspect-based-summarization-with-self-aspect","title":"Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation","date":"2025-04-17","arxiv_id":"2504.13054","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-hallucination-synthetic-captions-for","title":"Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training","date":"2025-04-17","arxiv_id":"2504.13123","repositories_listed":0,"syntology":null},{"url":null,"slug":"qllm-do-we-really-need-a-mixing-network-for","title":"QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?","date":"2025-04-17","arxiv_id":"2504.12961","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-contrastive-decoding-with","title":"Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -","date":"2025-04-16","arxiv_id":"2504.12137","repositories_listed":0,"syntology":null},{"url":null,"slug":"naming-is-framing-how-cybersecurity-s","title":"Naming is framing: How cybersecurity's language problems are repeating in AI governance","date":"2025-04-16","arxiv_id":"2504.13957","repositories_listed":0,"syntology":null},{"url":null,"slug":"purposefully-induced-psychosis-pip-embracing","title":"Purposefully Induced Psychosis (PIP): Embracing Hallucination as Imagination in Large Language Models","date":"2025-04-16","arxiv_id":"2504.12012","repositories_listed":0,"syntology":null}],"record_sha256":"891f83f3a1460158168d4bc35e95931fa7d9c2ff42f08bf52405b19c2db2ecf3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}