{"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/12","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":12,"pages_in_order":19,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/hallucination/papers/13","papers":[{"url":null,"slug":"steps-are-all-you-need-rethinking-stem","title":"Steps are all you need: Rethinking STEM Education with Prompt Engineering","date":"2024-12-06","arxiv_id":"2412.05023","repositories_listed":0,"syntology":null},{"url":null,"slug":"verb-mirage-unveiling-and-assessing-verb","title":"Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models","date":"2024-12-06","arxiv_id":"2412.04939","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-priors-for-satellite-image-restoration","title":"Deep priors for satellite image restoration with accurate uncertainties","date":"2024-12-05","arxiv_id":"2412.04130","repositories_listed":0,"syntology":null},{"url":null,"slug":"genmac-compositional-text-to-video-generation","title":"GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration","date":"2024-12-05","arxiv_id":"2412.04440","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-tool-hallucination-via-reliability","title":"Reducing Tool Hallucination via Reliability Alignment","date":"2024-12-05","arxiv_id":"2412.04141","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidhalluc-evaluating-temporal-hallucinations","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","date":"2024-12-04","arxiv_id":"2412.03735","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-brings-the-frisbee-probing-hidden","title":"Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis","date":"2024-12-04","arxiv_id":"2412.02946","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evolutionary-large-language-model-for","title":"An Evolutionary Large Language Model for Hallucination Mitigation","date":"2024-12-03","arxiv_id":"2412.02790","repositories_listed":0,"syntology":null},{"url":null,"slug":"cc-ocr-a-comprehensive-and-challenging-ocr","title":"CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy","date":"2024-12-03","arxiv_id":"2412.02210","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-benchmarks-and-datasets-for-llm-evaluation","title":"AI Benchmarks and Datasets for LLM Evaluation","date":"2024-12-02","arxiv_id":"2412.01020","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-logit-lens-contextual-embeddings-for","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","date":"2024-11-28","arxiv_id":"2411.19187","repositories_listed":0,"syntology":null},{"url":null,"slug":"dhcp-detecting-hallucinations-by-cross-modal","title":"DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models","date":"2024-11-27","arxiv_id":"2411.18659","repositories_listed":0,"syntology":null},{"url":null,"slug":"opcap-object-aware-prompting-captioning","title":"OPCap:Object-aware Prompting Captioning","date":"2024-11-27","arxiv_id":"2412.00095","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-topic-level-self-correctional-approach-to","title":"A Topic-level Self-Correctional Approach to Mitigate Hallucinations in MLLMs","date":"2024-11-26","arxiv_id":"2411.17265","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai2t-building-trustable-ai-tutors-by","title":"AI2T: Building Trustable AI Tutors by Interactively Teaching a Self-Aware Learning Agent","date":"2024-11-26","arxiv_id":"2411.17924","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-self-improvement-in-multimodal","title":"Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach","date":"2024-11-26","arxiv_id":"2411.17760","repositories_listed":0,"syntology":null},{"url":null,"slug":"meaningless-is-better-hashing-bias-inducing","title":"Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning","date":"2024-11-26","arxiv_id":"2411.17304","repositories_listed":0,"syntology":null},{"url":"/paper/vlrewardbench-a-challenging-benchmark-for","slug":"vlrewardbench-a-challenging-benchmark-for","title":"VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","date":"2024-11-26","arxiv_id":"2411.17451","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-multi-agent-consensus-through-third","title":"Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models","date":"2024-11-25","arxiv_id":"2411.16189","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-hallucinations-in-virtual-histology","title":"Detecting Hallucinations in Virtual Histology with Neural Precursors","date":"2024-11-22","arxiv_id":"2411.15060","repositories_listed":0,"syntology":null},{"url":null,"slug":"ict-image-object-cross-level-trusted","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","date":"2024-11-22","arxiv_id":"2411.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-llms-for-legacy-code-modernization","title":"Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation","date":"2024-11-22","arxiv_id":"2411.14971","repositories_listed":0,"syntology":null},{"url":null,"slug":"sycophancy-in-large-language-models-causes","title":"Sycophancy in Large Language Models: Causes and Mitigations","date":"2024-11-22","arxiv_id":"2411.15287","repositories_listed":0,"syntology":null},{"url":null,"slug":"catch-complementary-adaptive-token-level","title":"CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs","date":"2024-11-19","arxiv_id":"2411.12713","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-open-source-llms-enhance-data","title":"Can Open-source LLMs Enhance Data Synthesis for Toxic Detection?: An Experimental Study","date":"2024-11-18","arxiv_id":"2411.15175","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-knowledge-conflicts-in-language","title":"Mitigating Knowledge Conflicts in Language Model-Driven Question Answering","date":"2024-11-18","arxiv_id":"2411.11344","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-explainable-recommendation-in-e","title":"Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph","date":"2024-11-17","arxiv_id":"2412.01837","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-assisted-physical-invariant-extraction","title":"INVARLLM: LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection","date":"2024-11-17","arxiv_id":"2411.10918","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-multimodal-llms-the-mechanistic","title":"Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering","date":"2024-11-17","arxiv_id":"2411.10950","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-approach-to-eliminating","title":"A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery","date":"2024-11-16","arxiv_id":"2411.12759","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-programming-cop-empowering-large","title":"Chain-of-Programming (CoP) : Empowering Large Language Models for Geospatial Code Generation","date":"2024-11-16","arxiv_id":"2411.10753","repositories_listed":0,"syntology":null},{"url":null,"slug":"vibe-a-text-to-video-benchmark-for-evaluating","title":"ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models","date":"2024-11-16","arxiv_id":"2411.10867","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-importance-and-hallucination-analysis","title":"Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity","date":"2024-11-15","arxiv_id":"2411.10069","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-in-multimodal-large","title":"Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization","date":"2024-11-15","arxiv_id":"2411.10436","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-clearly-by-layer-two-enhancing","title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs","date":"2024-11-15","arxiv_id":"2411.09968","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-hallucination-reasoning-with-zero-shot","title":"LLM Hallucination Reasoning with Zero-shot Knowledge Test","date":"2024-11-14","arxiv_id":"2411.09689","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-limits-of-language-generation-trade","title":"On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse","date":"2024-11-14","arxiv_id":"2411.09642","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-general-to-specific-utilizing-general","title":"SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing Agents","date":"2024-11-12","arxiv_id":"2411.07965","repositories_listed":0,"syntology":null},{"url":null,"slug":"trustful-llms-customizing-and-grounding-text","title":"Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders","date":"2024-11-12","arxiv_id":"2411.07870","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-accuracy-of-chatbots-in","title":"Evaluating the Accuracy of Chatbots in Financial Literature","date":"2024-11-11","arxiv_id":"2411.07031","repositories_listed":0,"syntology":null},{"url":null,"slug":"invar-rag-invariant-llm-aligned-retrieval-for","title":"Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation","date":"2024-11-11","arxiv_id":"2411.07021","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-efficient-fine-tuning-for-gpt-like","title":"Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques","date":"2024-11-10","arxiv_id":"2411.06445","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucination-with-zerog-an","title":"Mitigating Hallucination with ZeroG: An Advanced Knowledge Management Engine","date":"2024-11-08","arxiv_id":"2411.05936","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-through-the-fog-a-cost-effectiveness","title":"Seeing Through the Fog: A Cost-Effectiveness Analysis of Hallucination Detection Systems","date":"2024-11-08","arxiv_id":"2411.05270","repositories_listed":0,"syntology":null},{"url":null,"slug":"amsnet-kg-a-netlist-dataset-for-llm-based-ams","title":"AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG","date":"2024-11-07","arxiv_id":"2411.13560","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-r-a-framework-for-domain-adaptive","title":"LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAG","date":"2024-11-07","arxiv_id":"2411.04476","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-guided-internal-states-for","title":"Prompt-Guided Internal States for Hallucination Detection of Large Language Models","date":"2024-11-07","arxiv_id":"2411.04847","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-guidance-for-retrievers","title":"Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation","date":"2024-11-06","arxiv_id":"2411.03957","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-vision-language-model-for","title":"Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extraction","date":"2024-11-06","arxiv_id":"2411.03707","repositories_listed":0,"syntology":null},{"url":null,"slug":"h-pope-hierarchical-polling-based-probing","title":"H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models","date":"2024-11-06","arxiv_id":"2411.04077","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-llm-enabled-extraction-of-synthesis","title":"Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature","date":"2024-11-05","arxiv_id":"2411.03484","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-vision-language-models-for-1","title":"Leveraging Vision-Language Models for Manufacturing Feature Recognition in CAD Designs","date":"2024-11-05","arxiv_id":"2411.02810","repositories_listed":0,"syntology":null},{"url":null,"slug":"veritas-a-unified-approach-to-reliability","title":"VERITAS: A Unified Approach to Reliability Evaluation","date":"2024-11-05","arxiv_id":"2411.03300","repositories_listed":0,"syntology":null},{"url":null,"slug":"clear-robust-context-guided-generative","title":"CleAR: Robust Context-Guided Generative Lighting Estimation for Mobile Augmented Reality","date":"2024-11-04","arxiv_id":"2411.02179","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-scientific-hypothesis-generation","title":"Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models","date":"2024-11-04","arxiv_id":"2411.02382","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-plug-and-play-methods-for-highly","title":"Robust plug-and-play methods for highly accelerated non-Cartesian MRI reconstruction","date":"2024-11-04","arxiv_id":"2411.01955","repositories_listed":0,"syntology":null},{"url":null,"slug":"radflag-a-black-box-hallucination-detection","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","date":"2024-11-01","arxiv_id":"2411.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-source-retrieval-augmented","title":"Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval","date":"2024-11-01","arxiv_id":"2411.00689","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-knowledge-mismatch-hypothesis","title":"Exploring the Knowledge Mismatch Hypothesis: Hallucination Propensity in Small Models Fine-tuned on Data from Larger Models","date":"2024-10-31","arxiv_id":"2411.00878","repositories_listed":0,"syntology":null},{"url":null,"slug":"improbable-bigrams-expose-vulnerabilities-of","title":"Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers","date":"2024-10-31","arxiv_id":"2410.23684","repositories_listed":0,"syntology":null},{"url":null,"slug":"ef-llm-energy-forecasting-llm-with-ai","title":"EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection","date":"2024-10-30","arxiv_id":"2411.00852","repositories_listed":0,"syntology":null},{"url":null,"slug":"visaidmath-benchmarking-visual-aided","title":"VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning","date":"2024-10-30","arxiv_id":"2410.22995","repositories_listed":0,"syntology":null},{"url":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","repositories_listed":0,"syntology":null},{"url":null,"slug":"marco-multi-agent-real-time-chat","title":"MARCO: Multi-Agent Real-time Chat Orchestration","date":"2024-10-29","arxiv_id":"2410.21784","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-perspective-for-adapting-generalist-ai-to","title":"A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges","date":"2024-10-28","arxiv_id":"2411.00024","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-debate-driven-experiment-on-llm","title":"A Debate-Driven Experiment on LLM Hallucinations and Accuracy","date":"2024-10-25","arxiv_id":"2410.19485","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-hallucinations-for-image","title":"Conditional Hallucinations for Image Compression","date":"2024-10-25","arxiv_id":"2410.19493","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-role-of-prompting-and","title":"Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models","date":"2024-10-25","arxiv_id":"2410.19385","repositories_listed":0,"syntology":null},{"url":null,"slug":"visioncoder-empowering-multi-agent-auto","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","date":"2024-10-25","arxiv_id":"2410.19245","repositories_listed":0,"syntology":null},{"url":"/paper/avhbench-a-cross-modal-hallucination","slug":"avhbench-a-cross-modal-hallucination","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","date":"2024-10-23","arxiv_id":"2410.18325","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/avhbench-a-cross-modal-hallucination#ran","syntology_url":"https://syntology.ai/paper/2410.18325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18325"}},"official":null}},{"url":null,"slug":"leveraging-the-domain-adaptation-of-retrieval","title":"Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination","date":"2024-10-23","arxiv_id":"2410.17783","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-hallucination-gaps-in-large","title":"Multilingual Hallucination Gaps in Large Language Models","date":"2024-10-23","arxiv_id":"2410.18270","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-robot-snakes-dream-like-electric-sheep","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","date":"2024-10-22","arxiv_id":"2410.17477","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-large-language-models-to-1","title":"Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy","date":"2024-10-22","arxiv_id":"2410.17234","repositories_listed":0,"syntology":null},{"url":null,"slug":"geocode-gpt-a-large-language-model-for","title":"GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks","date":"2024-10-22","arxiv_id":"2410.17031","repositories_listed":0,"syntology":null},{"url":null,"slug":"ipl-leveraging-multimodal-large-language","title":"IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing","date":"2024-10-22","arxiv_id":"2410.16977","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-hardened-and-hallucination-resistant","title":"Privacy-hardened and hallucination-resistant synthetic data generation with logic-solvers","date":"2024-10-22","arxiv_id":"2410.16705","repositories_listed":0,"syntology":null},{"url":null,"slug":"sg-fsm-a-self-guiding-zero-shot-prompting","title":"SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine","date":"2024-10-22","arxiv_id":"2410.17021","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-enabled-multiagent","title":"Large language models enabled multiagent ensemble method for efficient EHR data labeling","date":"2024-10-21","arxiv_id":"2410.16543","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-generate-and-evaluate-fact","title":"Learning to Generate and Evaluate Fact-checking Explanations with Transformers","date":"2024-10-21","arxiv_id":"2410.15669","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-of-large-language-1","title":"Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding","date":"2024-10-21","arxiv_id":"2410.15702","repositories_listed":0,"syntology":null},{"url":null,"slug":"netsafe-exploring-the-topological-safety-of","title":"NetSafe: Exploring the Topological Safety of Multi-agent Networks","date":"2024-10-21","arxiv_id":"2410.15686","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-reliable-offline-personal-ai","title":"Towards a Reliable Offline Personal AI Assistant for Long Duration Spaceflight","date":"2024-10-21","arxiv_id":"2410.16397","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-hallucination-in-large-visual","title":"A Survey of Hallucination in Large Visual Language Models","date":"2024-10-20","arxiv_id":"2410.15359","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detox-sensitive-neuron-dropout","title":"Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training","date":"2024-10-20","arxiv_id":"2410.15460","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-highlighting-reducing","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","date":"2024-10-19","arxiv_id":"2410.15116","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-parenting-is-all-you-need-multi-agentic","title":"Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation","date":"2024-10-18","arxiv_id":"2410.14262","repositories_listed":0,"syntology":null},{"url":null,"slug":"etf-an-entity-tracing-framework-for","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","date":"2024-10-17","arxiv_id":"2410.14748","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-large-language-models-in-an","title":"Utilizing Large Language Models in an iterative paradigm with domain feedback for zero-shot molecule optimization","date":"2024-10-17","arxiv_id":"2410.13147","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlled-automatic-task-specific-synthetic","title":"Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detection","date":"2024-10-16","arxiv_id":"2410.12278","repositories_listed":0,"syntology":null},{"url":null,"slug":"iter-ahmcl-alleviate-hallucination-for-large","title":"Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning","date":"2024-10-16","arxiv_id":"2410.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-a-scale-from-1-to-5-quantifying","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","date":"2024-10-16","arxiv_id":"2410.12222","repositories_listed":0,"syntology":null},{"url":null,"slug":"parametric-graph-representations-in-the-era","title":"What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs","date":"2024-10-16","arxiv_id":"2410.12126","repositories_listed":0,"syntology":null},{"url":null,"slug":"rosepo-aligning-llm-based-recommenders-with","title":"RosePO: Aligning LLM-based Recommenders with Human Values","date":"2024-10-16","arxiv_id":"2410.12519","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentigraph-an-interactive-knowledge-graph","title":"AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data","date":"2024-10-15","arxiv_id":"2410.11531","repositories_listed":0,"syntology":null},{"url":null,"slug":"have-the-vlms-lost-confidence-a-study-of","title":"Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs","date":"2024-10-15","arxiv_id":"2410.11302","repositories_listed":0,"syntology":null},{"url":null,"slug":"largepig-your-large-language-model-is","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","date":"2024-10-15","arxiv_id":"2410.11366","repositories_listed":0,"syntology":null},{"url":null,"slug":"magnifier-prompt-tackling-multimodal","title":"Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple Instructions","date":"2024-10-15","arxiv_id":"2410.11701","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-capacity-of-citation-generation-by","title":"On the Capacity of Citation Generation by Large Language Models","date":"2024-10-15","arxiv_id":"2410.11217","repositories_listed":0,"syntology":null}],"record_sha256":"c6eeb2030d9dc357cf1c1f50e09450c56bf4a25ccdf340c49b687a1856958f8d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}