{"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/13","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":13,"pages_in_order":19,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/task/hallucination/papers/14","papers":[{"url":null,"slug":"redeep-detecting-hallucination-in-retrieval","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","date":"2024-10-15","arxiv_id":"2410.11414","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-structured-data-reduce-epistemic","title":"Can Structured Data Reduce Epistemic Uncertainty?","date":"2024-10-14","arxiv_id":"2410.11141","repositories_listed":0,"syntology":null},{"url":null,"slug":"medico-towards-hallucination-detection-and","title":"Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion","date":"2024-10-14","arxiv_id":"2410.10408","repositories_listed":0,"syntology":null},{"url":null,"slug":"parenting-optimizing-knowledge-selection-of","title":"Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning","date":"2024-10-14","arxiv_id":"2410.10360","repositories_listed":0,"syntology":null},{"url":null,"slug":"skillaggregation-reference-free-llm-dependent","title":"SkillAggregation: Reference-free LLM-Dependent Aggregation","date":"2024-10-14","arxiv_id":"2410.10215","repositories_listed":0,"syntology":null},{"url":null,"slug":"collu-bench-a-benchmark-for-predicting","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","date":"2024-10-13","arxiv_id":"2410.09997","repositories_listed":0,"syntology":null},{"url":null,"slug":"honest-ai-fine-tuning-small-language-models","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","date":"2024-10-13","arxiv_id":"2410.09699","repositories_listed":0,"syntology":null},{"url":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","slug":"vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","arxiv_id":"2410.09421","repositories_listed":0,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset#ran","syntology_url":"https://syntology.ai/paper/2410.09421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09421"}},"official":null}},{"url":null,"slug":"measuring-the-inconsistency-of-large-language","title":"Measuring the Inconsistency of Large Language Models in Preferential Ranking","date":"2024-10-11","arxiv_id":"2410.08851","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-knowledge-graphs-make-large-language","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study over Open-ended Question Answering","date":"2024-10-10","arxiv_id":"2410.08085","repositories_listed":0,"syntology":null},{"url":null,"slug":"latteclip-unsupervised-clip-fine-tuning-via","title":"LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts","date":"2024-10-10","arxiv_id":"2410.08211","repositories_listed":0,"syntology":null},{"url":null,"slug":"publichearingbr-a-brazilian-portuguese","title":"PublicHearingBR: A Brazilian Portuguese Dataset of Public Hearing Transcripts for Summarization of Long Documents","date":"2024-10-10","arxiv_id":"2410.07495","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-pixels-to-tokens-revisiting-object","title":"From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models","date":"2024-10-09","arxiv_id":"2410.06795","repositories_listed":0,"syntology":null},{"url":null,"slug":"emma-empowering-multi-modal-mamba-with","title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","date":"2024-10-08","arxiv_id":"2410.05938","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-hallucination-detection-and-2","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.06304","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradual-learning-optimizing-fine-tuning-with","title":"Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models","date":"2024-10-08","arxiv_id":"2410.05802","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-to-the-patient-enhancing-medical","title":"Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation","date":"2024-10-08","arxiv_id":"2410.06094","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-enhanced-ethical-hacking-a-linux-focused","title":"AI-Enhanced Ethical Hacking: A Linux-Focused Experiment","date":"2024-10-07","arxiv_id":"2410.05105","repositories_listed":0,"syntology":null},{"url":null,"slug":"tldr-token-level-detective-reward-model-for","title":"TLDR: Token-Level Detective Reward Model for Large Vision Language Models","date":"2024-10-07","arxiv_id":"2410.04734","repositories_listed":0,"syntology":null},{"url":null,"slug":"damro-dive-into-the-attention-mechanism-of","title":"DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination","date":"2024-10-06","arxiv_id":"2410.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-using-ensemble-of","title":"Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to Enhance Mental Health Support","date":"2024-10-06","arxiv_id":"2410.10853","repositories_listed":0,"syntology":null},{"url":null,"slug":"didots-knowledge-distillation-from-large","title":"DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech","date":"2024-10-05","arxiv_id":"2410.04188","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-gda-automatic-domain-adaptation-for","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation","date":"2024-10-04","arxiv_id":"2410.03461","repositories_listed":0,"syntology":null},{"url":null,"slug":"sag-style-aligned-article-generation-via","title":"SAG: Style-Aligned Article Generation via Model Collaboration","date":"2024-10-04","arxiv_id":"2410.03137","repositories_listed":0,"syntology":null},{"url":null,"slug":"factcheckmate-preemptively-detecting-and","title":"FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs","date":"2024-10-03","arxiv_id":"2410.02899","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-training-data-attribution-for-large","title":"Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration","date":"2024-10-02","arxiv_id":"2410.01285","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmod-a-large-multimodal-ophthalmology-dataset","title":"LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models","date":"2024-10-02","arxiv_id":"2410.01620","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-labyrinth-of-links-navigating-the","title":"The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs","date":"2024-10-02","arxiv_id":"2410.01417","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoclip-xl-advancing-long-description","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","date":"2024-10-01","arxiv_id":"2410.00741","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-token-learning-with-similarity","title":"Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation","date":"2024-09-30","arxiv_id":"2409.19877","repositories_listed":0,"syntology":null},{"url":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhalu-hallucinations-in-responses-to","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","date":"2024-09-29","arxiv_id":"2409.19492","repositories_listed":0,"syntology":null},{"url":null,"slug":"deneb-a-hallucination-robust-automatic","title":"DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning","date":"2024-09-28","arxiv_id":"2409.19255","repositories_listed":0,"syntology":null},{"url":"/paper/haloscope-harnessing-unlabeled-llm","slug":"haloscope-harnessing-unlabeled-llm","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","date":"2024-09-26","arxiv_id":"2409.17504","repositories_listed":0,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/haloscope-harnessing-unlabeled-llm#ran","syntology_url":"https://syntology.ai/paper/2409.17504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17504"}},"official":null}},{"url":null,"slug":"enhancing-guardrails-for-safe-and-secure","title":"Enhancing Guardrails for Safe and Secure Healthcare AI","date":"2024-09-25","arxiv_id":"2409.17190","repositories_listed":0,"syntology":null},{"url":null,"slug":"rolebreak-character-hallucination-as-a","title":"RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems","date":"2024-09-25","arxiv_id":"2409.16727","repositories_listed":0,"syntology":null},{"url":null,"slug":"asthmabot-multi-modal-multi-lingual-retrieval","title":"AsthmaBot: Multi-modal, Multi-Lingual Retrieval Augmented Generation For Asthma Patient Support","date":"2024-09-24","arxiv_id":"2409.15815","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-text-to-sql-capabilities-of-large","title":"Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection","date":"2024-09-24","arxiv_id":"2409.15907","repositories_listed":0,"syntology":null},{"url":null,"slug":"planning-in-the-dark-llm-symbolic-planning","title":"Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts","date":"2024-09-24","arxiv_id":"2409.15915","repositories_listed":0,"syntology":null},{"url":null,"slug":"relep-a-novel-framework-for-real-world-long","title":"Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation","date":"2024-09-24","arxiv_id":"2409.15658","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-preliminary-study-of-o1-in-medicine-are-we","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","date":"2024-09-23","arxiv_id":"2409.15277","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-scientific-reproducibility-through","title":"Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications","date":"2024-09-23","arxiv_id":"2409.15076","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectively-enhancing-vision-language-large","title":"Effectively Enhancing Vision Language Large Models by Prompt Augmentation and Caption Utilization","date":"2024-09-22","arxiv_id":"2409.14484","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13994","title":"Contrastive Learning for Knowledge-Based Question Generation in Large Language Models","date":"2024-09-21","arxiv_id":"2409.13994","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13612","title":"FIHA: Autonomous Hallucination Evaluation in Vision-Language Models with Davidson Scene Graphs","date":"2024-09-20","arxiv_id":"2409.13612","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multiple-fill-in-the-blank-exam-approach","title":"A Multiple-Fill-in-the-Blank Exam Approach for Enhancing Zero-Resource Hallucination Detection in Large Language Models","date":"2024-09-20","arxiv_id":"2409.17173","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-check-their-own-results-to-mitigate","title":"LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks","date":"2024-09-19","arxiv_id":"2409.12580","repositories_listed":0,"syntology":null},{"url":null,"slug":"textualized-agent-style-reasoning-for-complex","title":"Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation","date":"2024-09-19","arxiv_id":"2409.12411","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-based-privileged-information-for","title":"Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB","date":"2024-09-17","arxiv_id":"2409.11104","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-resource-hallucination-detection-for","title":"Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling","date":"2024-09-17","arxiv_id":"2409.11283","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-resource-consumption-in-diffusion","title":"Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection","date":"2024-09-16","arxiv_id":"2409.10597","repositories_listed":0,"syntology":null},{"url":null,"slug":"sfr-rag-towards-contextually-faithful-llms","title":"SFR-RAG: Towards Contextually Faithful LLMs","date":"2024-09-16","arxiv_id":"2409.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-the-hallucination-on-low-level","title":"Explore the Hallucination on Low-level Perception for MLLMs","date":"2024-09-15","arxiv_id":"2409.09748","repositories_listed":0,"syntology":null},{"url":null,"slug":"ode-open-set-evaluation-of-hallucinations-in","title":"ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models","date":"2024-09-14","arxiv_id":"2409.09318","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-solution-for-meta-kdd-cup-24","title":"Winning Solution For Meta KDD Cup' 24","date":"2024-09-13","arxiv_id":"2410.00005","repositories_listed":0,"syntology":null},{"url":null,"slug":"medic-towards-a-comprehensive-framework-for","title":"MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications","date":"2024-09-11","arxiv_id":"2409.07314","repositories_listed":0,"syntology":null},{"url":null,"slug":"safety-challenges-of-ai-in-medicine","title":"Safety challenges of AI in medicine in the era of large language models","date":"2024-09-11","arxiv_id":"2409.18968","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-visual-language-1","title":"Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding","date":"2024-09-10","arxiv_id":"2409.06485","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-will-always-hallucinate-and-we-need-to","title":"LLMs Will Always Hallucinate, and We Need to Live With This","date":"2024-09-09","arxiv_id":"2409.05746","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-llms-and-knowledge-graphs-to-reduce","title":"Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering","date":"2024-09-06","arxiv_id":"2409.04181","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-buggy-contracts-via-smart-testing","title":"Detecting Buggy Contracts via Smart Testing","date":"2024-09-06","arxiv_id":"2409.04597","repositories_listed":0,"syntology":null},{"url":null,"slug":"vietnamese-legal-information-retrieval-in","title":"Vietnamese Legal Information Retrieval in Question-Answering System","date":"2024-09-05","arxiv_id":"2409.13699","repositories_listed":0,"syntology":null},{"url":null,"slug":"clue-concept-level-uncertainty-estimation-for","title":"CLUE: Concept-Level Uncertainty Estimation for Large Language Models","date":"2024-09-04","arxiv_id":"2409.03021","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-single-camera-bev-perception-using","title":"Improved Single Camera BEV Perception Using Multi-Camera Training","date":"2024-09-04","arxiv_id":"2409.02676","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-does-it-take-to-get-state-of-the-art-in","title":"What does it take to get state of the art in simultaneous speech-to-speech translation?","date":"2024-09-02","arxiv_id":"2409.00965","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-hallucinate-graphs-too-a-structural","title":"LLMs Prompted for Graphs: Hallucinations and Generative Capabilities","date":"2024-08-30","arxiv_id":"2409.00159","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-multimodal-hallucination","title":"Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data","date":"2024-08-30","arxiv_id":"2409.00238","repositories_listed":0,"syntology":null},{"url":null,"slug":"usersumbench-a-benchmark-framework-for","title":"UserSumBench: A Benchmark Framework for Evaluating User Summarization Approaches","date":"2024-08-30","arxiv_id":"2408.16966","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidence-enhanced-triplet-generation","title":"Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering","date":"2024-08-27","arxiv_id":"2408.15037","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-text-summarization-factuality-using","title":"Measuring text summarization factuality using atomic facts entailment metrics in the context of retrieval augmented generation","date":"2024-08-27","arxiv_id":"2408.15171","repositories_listed":0,"syntology":null},{"url":null,"slug":"negation-blindness-in-large-language-models","title":"Negation Blindness in Large Language Models: Unveiling the NO Syndrome in Image Generation","date":"2024-08-27","arxiv_id":"2409.00105","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-reliable-medical-question-answering","title":"Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models","date":"2024-08-25","arxiv_id":"2408.13808","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llm-be-a-good-path-planner-based-on","title":"Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning","date":"2024-08-23","arxiv_id":"2408.13184","repositories_listed":0,"syntology":null},{"url":null,"slug":"internal-and-external-knowledge-interactive","title":"Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering","date":"2024-08-23","arxiv_id":"2408.12979","repositories_listed":0,"syntology":null},{"url":null,"slug":"meddit-a-knowledge-controlled-diffusion","title":"MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient","date":"2024-08-22","arxiv_id":"2408.12236","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-optimized-tibetan-tourism-llms-enhancing","title":"RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization","date":"2024-08-21","arxiv_id":"2408.12003","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-analyzing-and-mitigating-sycophancy","title":"Towards Analyzing and Mitigating Sycophancy in Large Vision-Language Models","date":"2024-08-21","arxiv_id":"2408.11261","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-dpo-vision-language-models-as-a-source","title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs","date":"2024-08-19","arxiv_id":"2408.10433","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-document-retrieval-with-topic","title":"Enhanced document retrieval with topic embeddings","date":"2024-08-19","arxiv_id":"2408.10435","repositories_listed":0,"syntology":null},{"url":null,"slug":"maple-enhancing-review-generation-with-multi","title":"MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation","date":"2024-08-19","arxiv_id":"2408.09865","repositories_listed":0,"syntology":null},{"url":null,"slug":"cognitive-llms-towards-integrating-cognitive","title":"Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making","date":"2024-08-17","arxiv_id":"2408.09176","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-might-not-care-what-you","title":"Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions","date":"2024-08-16","arxiv_id":"2408.08780","repositories_listed":0,"syntology":null},{"url":null,"slug":"lower-layer-matters-alleviating-hallucination","title":"Lower Layer Matters: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused","date":"2024-08-16","arxiv_id":"2408.08769","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-with-code-comparing-approaches-for","title":"Plan with Code: Comparing approaches for robust NL to DSL generation","date":"2024-08-15","arxiv_id":"2408.08335","repositories_listed":0,"syntology":null},{"url":null,"slug":"codemirage-hallucinations-in-code-generated","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","date":"2024-08-14","arxiv_id":"2408.08333","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-language-models-on-the-knowledge","title":"Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability","date":"2024-08-14","arxiv_id":"2408.07852","repositories_listed":0,"syntology":null},{"url":null,"slug":"audit-llm-multi-agent-collaboration-for-log","title":"Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection","date":"2024-08-12","arxiv_id":"2408.08902","repositories_listed":0,"syntology":null},{"url":null,"slug":"reference-free-hallucination-detection-for","title":"Reference-free Hallucination Detection for Large Vision-Language Models","date":"2024-08-11","arxiv_id":"2408.05767","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-whisper-s-recognition-performance","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","date":"2024-08-10","arxiv_id":"2408.05554","repositories_listed":0,"syntology":null},{"url":null,"slug":"fist-financial-style-transfer-with","title":"FiSTECH: Financial Style Transfer to Enhance Creativity without Hallucinations in LLMs","date":"2024-08-09","arxiv_id":"2408.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03297","title":"KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models","date":"2024-08-06","arxiv_id":"2408.03297","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01916","title":"MAO: A Framework for Process Model Generation with Multi-Agent Orchestration","date":"2024-08-04","arxiv_id":"2408.01916","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01877","title":"Improving Zero-Shot ObjectNav with Generative Communication","date":"2024-08-03","arxiv_id":"2408.01877","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01003","title":"Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models","date":"2024-08-02","arxiv_id":"2408.01003","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01168","title":"Misinforming LLMs: vulnerabilities, challenges and opportunities","date":"2024-08-02","arxiv_id":"2408.01168","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00555","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","date":"2024-08-01","arxiv_id":"2408.00555","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21368","title":"Prompting Medical Large Vision-Language Models to Diagnose Pathologies by Visual Question Answering","date":"2024-07-31","arxiv_id":"2407.21368","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21424","title":"Cost-Effective Hallucination Detection for LLMs","date":"2024-07-31","arxiv_id":"2407.21424","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-and-mitigating-hallucination-in","title":"Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate","date":"2024-07-30","arxiv_id":"2407.20505","repositories_listed":0,"syntology":null},{"url":"/paper/vila-2-vila-augmented-vila","slug":"vila-2-vila-augmented-vila","title":"VILA$^2$: VILA Augmented VILA","date":"2024-07-24","arxiv_id":"2407.17453","repositories_listed":0,"syntology":null}],"record_sha256":"55a8fb10b8b339ded3e803f88cdc7e4fbc7e65bcbc7105a89e4ab38bb6c923b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}