{"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/10","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":10,"pages_in_order":19,"rows_per_page":100,"rows":[901,1000],"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/9","next":"/task/hallucination/papers/11","papers":[{"url":"/paper/self-alignment-of-large-video-language-models","slug":"self-alignment-of-large-video-language-models","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","date":"2025-04-16","arxiv_id":"2504.12083","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-misleading-queries-to-accurate-answers-a","title":"From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs","date":"2025-04-15","arxiv_id":"2504.11277","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-aware-generative-pretrained","title":"Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control","date":"2025-04-15","arxiv_id":"2504.10831","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detection-in-llms-via","title":"Hallucination Detection in LLMs via Topological Divergence on Attention Graphs","date":"2025-04-14","arxiv_id":"2504.10063","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-mllm-prompting-is-adaptive-a","title":"The Future of MLLM Prompting is Adaptive: A Comprehensive Experimental Evaluation of Prompt Engineering Methods for Robust Multimodal Performance","date":"2025-04-14","arxiv_id":"2504.10179","repositories_listed":0,"syntology":null},{"url":null,"slug":"ditse-high-fidelity-generative-speech","title":"DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers","date":"2025-04-13","arxiv_id":"2504.09381","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-mathematical-reasoning-in-large","title":"Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection","date":"2025-04-13","arxiv_id":"2504.09440","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthtrips-a-knowledge-grounded-framework-for","title":"SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders","date":"2025-04-12","arxiv_id":"2504.09277","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-document-cross-lingual-natural-language","title":"Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction","date":"2025-04-11","arxiv_id":"2504.12324","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-reliability-and-the-role-of","title":"Hallucination, reliability, and the role of generative AI in science","date":"2025-04-11","arxiv_id":"2504.08526","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhal-an-evaluation-dataset-for-medical","title":"MedHal: An Evaluation Dataset for Medical Hallucination Detection","date":"2025-04-11","arxiv_id":"2504.08596","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-in-collaborative-academic","title":"Generative AI in Collaborative Academic Report Writing: Advantages, Disadvantages, and Ethical Considerations","date":"2025-04-10","arxiv_id":"2504.08832","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-detect-and-defeat-molecular-mirage-a","title":"How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension","date":"2025-04-10","arxiv_id":"2504.12314","repositories_listed":0,"syntology":null},{"url":"/paper/robust-hallucination-detection-in-llms-via","slug":"robust-hallucination-detection-in-llms-via","title":"Robust Hallucination Detection in LLMs via Adaptive Token Selection","date":"2025-04-10","arxiv_id":"2504.07863","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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","sample_list":"/paper/robust-hallucination-detection-in-llms-via#ran","syntology_url":"https://syntology.ai/paper/2504.07863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07863"}},"official":null}},{"url":null,"slug":"endowing-embodied-agents-with-spatial","title":"Endowing Embodied Agents with Spatial Reasoning Capabilities for Vision-and-Language Navigation","date":"2025-04-09","arxiv_id":"2504.08806","repositories_listed":0,"syntology":null},{"url":null,"slug":"olmotrace-tracing-language-model-outputs-back","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","date":"2025-04-09","arxiv_id":"2504.07096","repositories_listed":0,"syntology":null},{"url":null,"slug":"perception-in-reflection","title":"Perception in Reflection","date":"2025-04-09","arxiv_id":"2504.07165","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-approaches-and-functionalities-in","title":"Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey","date":"2025-04-08","arxiv_id":"2504.10499","repositories_listed":0,"syntology":null},{"url":null,"slug":"capturing-ai-s-attention-physics-of","title":"Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond","date":"2025-04-06","arxiv_id":"2504.04600","repositories_listed":0,"syntology":null},{"url":null,"slug":"tarac-mitigating-hallucination-in-lvlms-via","title":"TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection","date":"2025-04-05","arxiv_id":"2504.04099","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-lms-and-generative-ai-dynamic-course","title":"Bridging LMS and Generative AI: Dynamic Course Content Integration (DCCI) for Connecting LLMs to Course Content -- The Ask ME Assistant","date":"2025-04-04","arxiv_id":"2504.03966","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detection-on-a-budget-efficient","title":"Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy","date":"2025-04-04","arxiv_id":"2504.03579","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-poisoning-attacks-against-retrieval","title":"Practical Poisoning Attacks against Retrieval-Augmented Generation","date":"2025-04-04","arxiv_id":"2504.03957","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-memory-augmented-llm-driven-method-for","title":"A Memory-Augmented LLM-Driven Method for Autonomous Merging of 3D Printing Work Orders","date":"2025-04-03","arxiv_id":"2504.02509","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-virtual-mixture-of-experts","title":"A Unified Virtual Mixture-of-Experts Framework:Enhanced Inference and Hallucination Mitigation in Single-Model System","date":"2025-04-01","arxiv_id":"2504.03739","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphmaster-automated-graph-synthesis-via-llm","title":"GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments","date":"2025-04-01","arxiv_id":"2504.00711","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-illusionist-s-prompt-exposing-the-factual","title":"The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances","date":"2025-04-01","arxiv_id":"2504.02865","repositories_listed":0,"syntology":null},{"url":"/paper/hoigen-1m-a-large-scale-dataset-for-human","slug":"hoigen-1m-a-large-scale-dataset-for-human","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","date":"2025-03-31","arxiv_id":"2503.23715","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/hoigen-1m-a-large-scale-dataset-for-human#ran","syntology_url":"https://syntology.ai/paper/2503.23715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23715"}},"official":null}},{"url":null,"slug":"an-analysis-of-decoding-methods-for-llm-based","title":"An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering","date":"2025-03-30","arxiv_id":"2503.23415","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-instruct-for-visual-instruction","title":"Learning to Instruct for Visual Instruction Tuning","date":"2025-03-28","arxiv_id":"2503.22215","repositories_listed":0,"syntology":null},{"url":null,"slug":"alleviating-llm-based-generative-retrieval","title":"Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search","date":"2025-03-27","arxiv_id":"2503.21098","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-evaluation-models-for-rag-who","title":"Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best?","date":"2025-03-27","arxiv_id":"2503.21157","repositories_listed":0,"syntology":null},{"url":null,"slug":"tricking-retrievers-with-influential-tokens","title":"Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack","date":"2025-03-27","arxiv_id":"2503.21315","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-oriented-preference-alignment-for","title":"Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs","date":"2025-03-26","arxiv_id":"2503.20309","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-low-level-visual-hallucinations","title":"Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy","date":"2025-03-26","arxiv_id":"2503.20673","repositories_listed":0,"syntology":null},{"url":"/paper/tn-eval-rubric-and-evaluation-protocols-for","slug":"tn-eval-rubric-and-evaluation-protocols-for","title":"TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes","date":"2025-03-26","arxiv_id":"2503.20648","repositories_listed":0,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tn-eval-rubric-and-evaluation-protocols-for#ran","syntology_url":"https://syntology.ai/paper/2503.20648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20648"}},"official":null}},{"url":null,"slug":"vision-amplified-semantic-entropy-for","title":"Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering","date":"2025-03-26","arxiv_id":"2503.20504","repositories_listed":0,"syntology":null},{"url":null,"slug":"hausanlp-at-semeval-2025-task-3-towards-a","title":"HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection","date":"2025-03-25","arxiv_id":"2503.19650","repositories_listed":0,"syntology":null},{"url":null,"slug":"kshseek-data-driven-approaches-to-mitigating","title":"KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models","date":"2025-03-25","arxiv_id":"2503.19482","repositories_listed":0,"syntology":null},{"url":null,"slug":"shed-hd-a-shannon-entropy-distribution","title":"ShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices","date":"2025-03-23","arxiv_id":"2503.18242","repositories_listed":0,"syntology":null},{"url":null,"slug":"good4cir-generating-detailed-synthetic","title":"good4cir: Generating Detailed Synthetic Captions for Composed Image Retrieval","date":"2025-03-22","arxiv_id":"2503.17871","repositories_listed":0,"syntology":null},{"url":null,"slug":"factselfcheck-fact-level-black-box","title":"FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs","date":"2025-03-21","arxiv_id":"2503.17229","repositories_listed":0,"syntology":null},{"url":null,"slug":"judge-anything-mllm-as-a-judge-across-any","title":"Judge Anything: MLLM as a Judge Across Any Modality","date":"2025-03-21","arxiv_id":"2503.17489","repositories_listed":0,"syntology":null},{"url":null,"slug":"dna-bench-when-silence-is-smarter","title":"DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs","date":"2025-03-20","arxiv_id":"2503.15793","repositories_listed":0,"syntology":null},{"url":null,"slug":"eckgbench-benchmarking-large-language-models","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph","date":"2025-03-20","arxiv_id":"2503.15990","repositories_listed":0,"syntology":null},{"url":null,"slug":"mash-vlm-mitigating-action-scene","title":"MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations","date":"2025-03-20","arxiv_id":"2503.15871","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmdt-decoding-the-trustworthiness-and-safety","title":"MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models","date":"2025-03-19","arxiv_id":"2503.14827","repositories_listed":0,"syntology":null},{"url":"/paper/poly-fever-a-multilingual-fact-verification","slug":"poly-fever-a-multilingual-fact-verification","title":"Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models","date":"2025-03-19","arxiv_id":"2503.16541","repositories_listed":0,"syntology":null},{"url":null,"slug":"r-2-a-llm-based-novel-to-screenplay","title":"R$^2$: A LLM Based Novel-to-Screenplay Generation Framework with Causal Plot Graphs","date":"2025-03-19","arxiv_id":"2503.15655","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-llm-generation-with-knowledge","title":"Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine","date":"2025-03-18","arxiv_id":"2503.16530","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-hallucination-to-suture-insights-from","title":"From \"Hallucination\" to \"Suture\": Insights from Language Philosophy to Enhance Large Language Models","date":"2025-03-18","arxiv_id":"2503.14392","repositories_listed":0,"syntology":null},{"url":null,"slug":"rad-retrieval-augmented-decision-making-of","title":"RAD: Retrieval-Augmented Decision-Making of Meta-Actions with Vision-Language Models in Autonomous Driving","date":"2025-03-18","arxiv_id":"2503.13861","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmser-enhancing-sequential-recommendation","title":"LLMSeR: Enhancing Sequential Recommendation via LLM-based Data Augmentation","date":"2025-03-16","arxiv_id":"2503.12547","repositories_listed":0,"syntology":null},{"url":null,"slug":"applications-of-large-language-model","title":"Applications of Large Language Model Reasoning in Feature Generation","date":"2025-03-15","arxiv_id":"2503.11989","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-agents-for-education-advances-and","title":"LLM Agents for Education: Advances and Applications","date":"2025-03-14","arxiv_id":"2503.11733","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-kg-il-a-multi-agent-hybrid-framework-for","title":"RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration","date":"2025-03-14","arxiv_id":"2503.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-inference-adaptively-for","title":"Learning to Inference Adaptively for Multimodal Large Language Models","date":"2025-03-13","arxiv_id":"2503.10905","repositories_listed":0,"syntology":null},{"url":null,"slug":"through-the-magnifying-glass-adaptive","title":"Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding","date":"2025-03-13","arxiv_id":"2503.10183","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-llms-hallucination-usable-llm-based","title":"Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection","date":"2025-03-12","arxiv_id":"2503.09153","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-hijackers-detect-and-disentangle","title":"Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation","date":"2025-03-11","arxiv_id":"2503.08216","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-reallocation-towards-zero-cost-and","title":"Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs","date":"2025-03-11","arxiv_id":"2503.08342","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-guided-attention-map-editing-towards","title":"Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation","date":"2025-03-11","arxiv_id":"2503.08963","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnipaint-mastering-object-oriented-editing","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","date":"2025-03-11","arxiv_id":"2503.08677","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-what-s-not-there-spurious-correlation","title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs","date":"2025-03-11","arxiv_id":"2503.08884","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-chinese-medical-llms-a-medbench","title":"Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies","date":"2025-03-10","arxiv_id":"2503.07306","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrlrag-black-box-adversarial-attacks-based","title":"CtrlRAG: Black-box Adversarial Attacks Based on Masked Language Models in Retrieval-Augmented Language Generation","date":"2025-03-10","arxiv_id":"2503.06950","repositories_listed":0,"syntology":null},{"url":null,"slug":"eazy-eliminating-hallucinations-in-lvlms-by","title":"EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens","date":"2025-03-10","arxiv_id":"2503.07772","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-in-yolo-based","title":"Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection","date":"2025-03-10","arxiv_id":"2503.07330","repositories_listed":0,"syntology":null},{"url":null,"slug":"callireader-contextualizing-chinese","title":"CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model","date":"2025-03-09","arxiv_id":"2503.06472","repositories_listed":0,"syntology":null},{"url":null,"slug":"perturbollava-reducing-multimodal","title":"PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training","date":"2025-03-09","arxiv_id":"2503.06486","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-hallucination-standards-for-domain","title":"Maximum Hallucination Standards for Domain-Specific Large Language Models","date":"2025-03-07","arxiv_id":"2503.05481","repositories_listed":0,"syntology":null},{"url":null,"slug":"sindex-semantic-inconsistency-index-for","title":"SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs","date":"2025-03-07","arxiv_id":"2503.05980","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-compress-bench-benchmarking-the-broader","title":"LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression","date":"2025-03-06","arxiv_id":"2503.04982","repositories_listed":0,"syntology":null},{"url":null,"slug":"tpc-cross-temporal-prediction-connection-for","title":"TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction","date":"2025-03-06","arxiv_id":"2503.04457","repositories_listed":0,"syntology":null},{"url":null,"slug":"dsvd-dynamic-self-verify-decoding-for","title":"DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models","date":"2025-03-05","arxiv_id":"2503.03149","repositories_listed":0,"syntology":null},{"url":null,"slug":"monitoring-decoding-mitigating-hallucination","title":"Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation","date":"2025-03-05","arxiv_id":"2503.03106","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-what-you-are-told-visual-attention-sink","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","date":"2025-03-05","arxiv_id":"2503.03321","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-text-hallucination-of","title":"Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias","date":"2025-03-05","arxiv_id":"2503.03595","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-a-sparse-autoencoder-based-framework-for","title":"SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs","date":"2025-03-04","arxiv_id":"2503.03032","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01075","title":"Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS","date":"2025-03-03","arxiv_id":"2503.01075","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01236","title":"LLM-Advisor: An LLM Benchmark for Cost-efficient Path Planning across Multiple Terrains","date":"2025-03-03","arxiv_id":"2503.01236","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptively-evaluating-models-with-task","title":"Adaptively profiling models with task elicitation","date":"2025-03-03","arxiv_id":"2503.01986","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-depression-detection-in-clinical","title":"Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation","date":"2025-03-03","arxiv_id":"2503.01315","repositories_listed":0,"syntology":null},{"url":null,"slug":"unmasking-digital-falsehoods-a-comparative","title":"Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies","date":"2025-03-02","arxiv_id":"2503.00724","repositories_listed":0,"syntology":null},{"url":null,"slug":"steer-llm-latents-for-hallucination-detection","title":"Steer LLM Latents for Hallucination Detection","date":"2025-03-01","arxiv_id":"2503.01917","repositories_listed":0,"syntology":null},{"url":"/paper/unifa-a-unified-feature-hallucination","slug":"unifa-a-unified-feature-hallucination","title":"UniFa: A unified feature hallucination framework for any-shot object detection","date":"2025-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"2502-21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","date":"2025-02-28","arxiv_id":"2502.21239","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-generalizability-of-factual","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization","date":"2025-02-26","arxiv_id":"2502.19127","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-importance-of-text-preprocessing-for","title":"On the Importance of Text Preprocessing for Multimodal Representation Learning and Pathology Report Generation","date":"2025-02-26","arxiv_id":"2502.19285","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-big-with-small-models-knowledge","title":"Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents","date":"2025-02-26","arxiv_id":"2502.19545","repositories_listed":0,"syntology":null},{"url":null,"slug":"brido-bringing-democratic-order-to","title":"BRIDO: Bringing Democratic Order to Abstractive Summarization","date":"2025-02-25","arxiv_id":"2502.18342","repositories_listed":0,"syntology":null},{"url":"/paper/stealthy-backdoor-attack-in-self-supervised","slug":"stealthy-backdoor-attack-in-self-supervised","title":"Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models","date":"2025-02-25","arxiv_id":"2502.18290","repositories_listed":0,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/stealthy-backdoor-attack-in-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2502.18290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18290"}},"official":null}},{"url":null,"slug":"exploring-causes-and-mitigation-of","title":"Exploring Causes and Mitigation of Hallucinations in Large Vision Language Models","date":"2025-02-24","arxiv_id":"2502.16842","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-is-hallucination-through-the","title":"`Generalization is hallucination' through the lens of tensor completions","date":"2025-02-24","arxiv_id":"2502.17305","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-law-of-knowledge-overshadowing-towards","title":"The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination","date":"2025-02-22","arxiv_id":"2502.16143","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-fusion-an-ensemble","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","date":"2025-02-22","arxiv_id":"2503.05757","repositories_listed":0,"syntology":null},{"url":null,"slug":"zigong-1-0-a-large-language-model-for","title":"ZiGong 1.0: A Large Language Model for Financial Credit","date":"2025-02-22","arxiv_id":"2502.16159","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-background-information-in","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","date":"2025-02-21","arxiv_id":"2502.15389","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detection-in-large-language","title":"Hallucination Detection in Large Language Models with Metamorphic Relations","date":"2025-02-20","arxiv_id":"2502.15844","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-struggle-to-describe","title":"Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of LLMs","date":"2025-02-20","arxiv_id":"2502.14748","repositories_listed":0,"syntology":null}],"record_sha256":"ecbdd72d24e1b3460c6ef976f2759168f27b1919980b3b10827a79e6c15efd4c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}