{"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/15","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":15,"pages_in_order":19,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/task/hallucination/papers/16","papers":[{"url":null,"slug":"navigating-llm-ethics-advancements-challenges","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","date":"2024-05-14","arxiv_id":"2406.18841","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-retrieval-augmented-large","title":"Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness","date":"2024-05-13","arxiv_id":"2405.08151","repositories_listed":0,"syntology":null},{"url":null,"slug":"control-token-with-dense-passage-retrieval","title":"Control Token with Dense Passage Retrieval","date":"2024-05-13","arxiv_id":"2405.13008","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-in-large-language","title":"Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval","date":"2024-05-10","arxiv_id":"2405.06545","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-find-mathematical-reasoning-mistakes","title":"LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought","date":"2024-05-09","arxiv_id":"2405.06705","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-eqa-tackling-situational-queries-in","title":"Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering","date":"2024-05-08","arxiv_id":"2405.04732","repositories_listed":0,"syntology":null},{"url":null,"slug":"deception-in-reinforced-autonomous-agents-the","title":"Deception in Reinforced Autonomous Agents","date":"2024-05-07","arxiv_id":"2405.04325","repositories_listed":0,"syntology":null},{"url":null,"slug":"sutra-scalable-multilingual-language-model","title":"SUTRA: Scalable Multilingual Language Model Architecture","date":"2024-05-07","arxiv_id":"2405.06694","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-capabilities-of-llms-across","title":"Quantifying the Capabilities of LLMs across Scale and Precision","date":"2024-05-06","arxiv_id":"2405.03146","repositories_listed":0,"syntology":null},{"url":null,"slug":"score-based-generative-priors-guided-model","title":"Score-based Generative Priors Guided Model-driven Network for MRI Reconstruction","date":"2024-05-05","arxiv_id":"2405.02958","repositories_listed":0,"syntology":null},{"url":null,"slug":"r4-reinforced-retriever-reorder-responder-for","title":"R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models","date":"2024-05-04","arxiv_id":"2405.02659","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasons-a-benchmark-for-retrieval-and","title":"Attribution in Scientific Literature: New Benchmark and Methods","date":"2024-05-03","arxiv_id":"2405.02228","repositories_listed":0,"syntology":null},{"url":null,"slug":"flame-factuality-aware-alignment-for-large","title":"FLAME: Factuality-Aware Alignment for Large Language Models","date":"2024-05-02","arxiv_id":"2405.01525","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-hallucinating-model-help-in-reducing","title":"Can a Hallucinating Model help in Reducing Human \"Hallucination\"?","date":"2024-05-01","arxiv_id":"2405.00843","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pyramid-of-captions","title":"What Makes for Good Image Captions?","date":"2024-05-01","arxiv_id":"2405.00485","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmonic-llms-are-trustworthy","title":"Harmonic LLMs are Trustworthy","date":"2024-04-30","arxiv_id":"2404.19708","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-fact-checker-enabling-high-fidelity","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","date":"2024-04-30","arxiv_id":"2404.19752","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-quality-and-hallucination","title":"A robust and scalable framework for hallucination detection in virtual tissue staining and digital pathology","date":"2024-04-29","arxiv_id":"2404.18458","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmac-copilot-multi-modal-agent-collaboration","title":"MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot","date":"2024-04-28","arxiv_id":"2404.18074","repositories_listed":0,"syntology":null},{"url":null,"slug":"serpent-vlm-self-refining-radiology-report","title":"SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models","date":"2024-04-27","arxiv_id":"2404.17912","repositories_listed":0,"syntology":null},{"url":null,"slug":"fake-artificial-intelligence-generated","title":"Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunities","date":"2024-04-25","arxiv_id":"2405.00711","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-foundational-large-language-models-assist","title":"Can Foundational Large Language Models Assist with Conducting Pharmaceuticals Manufacturing Investigations?","date":"2024-04-24","arxiv_id":"2404.15578","repositories_listed":0,"syntology":null},{"url":null,"slug":"ks-llm-knowledge-selection-of-large-language","title":"KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering","date":"2024-04-24","arxiv_id":"2404.15660","repositories_listed":0,"syntology":null},{"url":null,"slug":"finematch-aspect-based-fine-grained-image-and","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","date":"2024-04-23","arxiv_id":"2404.14715","repositories_listed":0,"syntology":null},{"url":null,"slug":"regressive-side-effects-of-training-language","title":"Student Data Paradox and Curious Case of Single Student-Tutor Model: Regressive Side Effects of Training LLMs for Personalized Learning","date":"2024-04-23","arxiv_id":"2404.15156","repositories_listed":0,"syntology":null},{"url":null,"slug":"skingen-an-explainable-dermatology-diagnosis","title":"SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models","date":"2024-04-23","arxiv_id":"2404.14755","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-sample-image-fusion-upsampling-of","title":"Single-sample image-fusion upsampling of fluorescence lifetime images","date":"2024-04-19","arxiv_id":"2404.13102","repositories_listed":0,"syntology":null},{"url":null,"slug":"textsquare-scaling-up-text-centric-visual","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","date":"2024-04-19","arxiv_id":"2404.12803","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-catch-the-elephant-the-evolvement-of","title":"Can We Catch the Elephant? A Survey of the Evolvement of Hallucination Evaluation on Natural Language Generation","date":"2024-04-18","arxiv_id":"2404.12041","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucibot-is-there-no-such-thing-as-a-bad","title":"Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing","date":"2024-04-18","arxiv_id":"2404.12535","repositories_listed":0,"syntology":null},{"url":null,"slug":"fact-teaching-mllms-with-faithful-concise-and","title":"Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales","date":"2024-04-17","arxiv_id":"2404.11129","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-computational-account-of-the-development","title":"A computational account of the development and evolution of psychotic symptoms","date":"2024-04-16","arxiv_id":"2404.10954","repositories_listed":0,"syntology":null},{"url":null,"slug":"fewer-truncations-improve-language-modeling","title":"Fewer Truncations Improve Language Modeling","date":"2024-04-16","arxiv_id":"2404.10830","repositories_listed":0,"syntology":null},{"url":null,"slug":"prescribing-the-right-remedy-mitigating","title":"Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning","date":"2024-04-16","arxiv_id":"2404.10332","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-on-efficient-knowledge-paths","title":"Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10384","repositories_listed":0,"syntology":null},{"url":null,"slug":"anatomy-of-industrial-scale-multilingual-asr","title":"Anatomy of Industrial Scale Multilingual ASR","date":"2024-04-15","arxiv_id":"2404.09841","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-guided-extrapolative-decoding-to","title":"Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models","date":"2024-04-14","arxiv_id":"2404.09338","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-semantic-thinking-a-robust-strategy-to","title":"Distilling Reasoning Ability from Large Language Models with Adaptive Thinking","date":"2024-04-14","arxiv_id":"2404.09170","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-hallucination-in-structured-outputs","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","date":"2024-04-12","arxiv_id":"2404.08189","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidently-nonsensical-a-critical-survey-on","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","date":"2024-04-11","arxiv_id":"2404.07461","repositories_listed":0,"syntology":null},{"url":null,"slug":"brave-broadening-the-visual-encoding-of","title":"BRAVE: Broadening the visual encoding of vision-language models","date":"2024-04-10","arxiv_id":"2404.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"metacheckgpt-a-multi-task-hallucination","title":"MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models","date":"2024-04-10","arxiv_id":"2404.06948","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-multimodal-long-form","title":"Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports","date":"2024-04-09","arxiv_id":"2404.06162","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-research-synthesis-with-domain","title":"Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning","date":"2024-04-08","arxiv_id":"2404.08680","repositories_listed":0,"syntology":null},{"url":null,"slug":"fgaif-aligning-large-vision-language-models","title":"FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback","date":"2024-04-07","arxiv_id":"2404.05046","repositories_listed":0,"syntology":null},{"url":null,"slug":"havtr-improving-video-text-retrieval-through","title":"HaVTR: Improving Video-Text Retrieval Through Augmentation Using Large Foundation Models","date":"2024-04-07","arxiv_id":"2404.05083","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperbolic-learning-with-synthetic-captions","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","date":"2024-04-07","arxiv_id":"2404.05016","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-limitations-of-large-language-models","title":"On the Limitations of Large Language Models (LLMs): False Attribution","date":"2024-04-06","arxiv_id":"2404.04631","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffn-skipllm-a-hidden-gem-for-autoregressive","title":"FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping","date":"2024-04-05","arxiv_id":"2404.03865","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cause-effect-look-at-alleviating","title":"A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation","date":"2024-04-04","arxiv_id":"2404.03491","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-llm-hallucinations-via-conformal","title":"Mitigating LLM Hallucinations via Conformal Abstention","date":"2024-04-04","arxiv_id":"2405.01563","repositories_listed":0,"syntology":null},{"url":null,"slug":"aloha-a-new-measure-for-hallucination-in","title":"ALOHa: A New Measure for Hallucination in Captioning Models","date":"2024-04-03","arxiv_id":"2404.02904","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-study-of-domain-driven-terms","title":"Comparative Study of Domain Driven Terms Extraction Using Large Language Models","date":"2024-04-02","arxiv_id":"2404.02330","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-norms-from-contracts-via-chatgpt","title":"Extracting Norms from Contracts Via ChatGPT: Opportunities and Challenges","date":"2024-04-02","arxiv_id":"2404.02269","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-diversity-aware-active-learning","title":"Hallucination Diversity-Aware Active Learning for Text Summarization","date":"2024-04-02","arxiv_id":"2404.01588","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-and-evaluating-hallucinations-in","title":"Exploring and Evaluating Hallucinations in LLM-Powered Code Generation","date":"2024-04-01","arxiv_id":"2404.00971","repositories_listed":0,"syntology":null},{"url":null,"slug":"factoid-factual-entailment-for-hallucination","title":"FACTOID: FACtual enTailment fOr hallucInation Detection","date":"2024-03-28","arxiv_id":"2403.19113","repositories_listed":0,"syntology":null},{"url":null,"slug":"rejection-improves-reliability-training-llms","title":"Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback","date":"2024-03-27","arxiv_id":"2403.18349","repositories_listed":0,"syntology":null},{"url":null,"slug":"sorry-come-again-prompting-enhancing","title":"\"Sorry, Come Again?\" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing","date":"2024-03-27","arxiv_id":"2403.18976","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-hallucination-definition","title":"Visual Hallucination: Definition, Quantification, and Prescriptive Remediations","date":"2024-03-26","arxiv_id":"2403.17306","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-lflh-learning-agile-navigation-in","title":"Dyna-LfLH: Learning Agile Navigation in Dynamic Environments from Learned Hallucination","date":"2024-03-25","arxiv_id":"2403.17231","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detection-in-foundation-models","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","date":"2024-03-25","arxiv_id":"2403.16527","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-semantic-reconstruction-to","title":"ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models","date":"2024-03-24","arxiv_id":"2403.16167","repositories_listed":0,"syntology":null},{"url":null,"slug":"cartoon-hallucinations-detection-pose-aware","title":"Make VLM Recognize Visual Hallucination on Cartoon Character Image with Pose Information","date":"2024-03-22","arxiv_id":"2403.15048","repositories_listed":0,"syntology":null},{"url":null,"slug":"sphere-neural-networks-for-rational-reasoning","title":"Sphere Neural-Networks for Rational Reasoning","date":"2024-03-22","arxiv_id":"2403.15297","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-hallucination-control-by-visual","title":"Multi-Modal Hallucination Control by Visual Information Grounding","date":"2024-03-20","arxiv_id":"2403.14003","repositories_listed":0,"syntology":null},{"url":null,"slug":"dee-dual-stage-explainable-evaluation-method","title":"DEE: Dual-stage Explainable Evaluation Method for Text Generation","date":"2024-03-18","arxiv_id":"2403.11509","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-imagine-plan-discovering-and","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","date":"2024-03-18","arxiv_id":"2403.13438","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-multi-task-hallucination-detection","title":"Zero-Shot Multi-task Hallucination Detection","date":"2024-03-18","arxiv_id":"2403.12244","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffmac-diffusion-manifold-hallucination","title":"DiffMAC: Diffusion Manifold Hallucination Correction for High Generalization Blind Face Restoration","date":"2024-03-15","arxiv_id":"2403.10098","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-dialogue-hallucination-for-large","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","date":"2024-03-15","arxiv_id":"2403.10492","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-twice-before-assure-confidence","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","date":"2024-03-15","arxiv_id":"2403.09972","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-hallucination-and-coverage-errors","title":"Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics","date":"2024-03-13","arxiv_id":"2403.08904","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-clinical-reasoning-with-large","title":"Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds","date":"2024-03-11","arxiv_id":"2403.06609","repositories_listed":0,"syntology":null},{"url":null,"slug":"kellmrec-knowledge-enhanced-large-language","title":"TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance","date":"2024-03-11","arxiv_id":"2403.06642","repositories_listed":0,"syntology":null},{"url":null,"slug":"put-myself-in-your-shoes-lifting-the","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","date":"2024-03-11","arxiv_id":"2403.06351","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-play-games-a-case","title":"Can Large Language Models Play Games? A Case Study of A Self-Play Approach","date":"2024-03-08","arxiv_id":"2403.05632","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatasu-evoking-llm-s-reflexion-to-truly","title":"ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues","date":"2024-03-08","arxiv_id":"2403.05326","repositories_listed":0,"syntology":null},{"url":null,"slug":"sora-as-an-agi-world-model-a-complete-survey","title":"Sora as an AGI World Model? A Complete Survey on Text-to-Video Generation","date":"2024-03-08","arxiv_id":"2403.05131","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-free-accountable-intervention-for-llm","title":"Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach","date":"2024-03-08","arxiv_id":"2403.05636","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-assessment-of-recent-large","title":"Effectiveness Assessment of Recent Large Vision-Language Models","date":"2024-03-07","arxiv_id":"2403.04306","repositories_listed":0,"syntology":null},{"url":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-and-mitigating-number","title":"Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models","date":"2024-03-03","arxiv_id":"2403.01373","repositories_listed":0,"syntology":null},{"url":null,"slug":"right-for-right-reasons-large-language-models","title":"Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering","date":"2024-03-03","arxiv_id":"2403.01390","repositories_listed":0,"syntology":null},{"url":null,"slug":"crimson-empowering-strategic-reasoning-in","title":"Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language Models","date":"2024-03-01","arxiv_id":"2403.00878","repositories_listed":0,"syntology":null},{"url":null,"slug":"malto-at-semeval-2024-task-6-leveraging","title":"MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection","date":"2024-03-01","arxiv_id":"2403.00964","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-hallucinations-for-reasoning-of","title":"Navigating Hallucinations for Reasoning of Unintentional Activities","date":"2024-02-29","arxiv_id":"2402.19405","repositories_listed":0,"syntology":null},{"url":null,"slug":"whispers-that-shake-foundations-analyzing-and","title":"Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models","date":"2024-02-29","arxiv_id":"2402.19103","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-decoding-of-critical-tokens-for","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","date":"2024-02-28","arxiv_id":"2402.17982","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-reliability-a-brief-overview-on","title":"Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models","date":"2024-02-27","arxiv_id":"2402.17671","repositories_listed":0,"syntology":null},{"url":"/paper/groundhog-grounding-large-language-models-to","slug":"groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","arxiv_id":"2402.16846","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-before-you-leap-towards-decision-aware","title":"Look Before You Leap: Towards Decision-Aware and Generalizable Tool-Usage for Large Language Models","date":"2024-02-26","arxiv_id":"2402.16696","repositories_listed":0,"syntology":null},{"url":null,"slug":"avi-talking-learning-audio-visual","title":"AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generation","date":"2024-02-25","arxiv_id":"2402.16124","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-software-engineering-in-the-era-of","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","date":"2024-02-25","arxiv_id":"2402.15943","repositories_listed":0,"syntology":null},{"url":null,"slug":"hal-eval-a-universal-and-fine-grained","title":"Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models","date":"2024-02-24","arxiv_id":"2402.15721","repositories_listed":0,"syntology":null},{"url":null,"slug":"carbd-ko-a-contextually-annotated-review","title":"CARBD-Ko: A Contextually Annotated Review Benchmark Dataset for Aspect-Level Sentiment Classification in Korean","date":"2024-02-23","arxiv_id":"2402.15046","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-the-generator-mind-its-contexts-an","title":"Does the Generator Mind its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer","date":"2024-02-22","arxiv_id":"2402.14488","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-and-dynamics-of-delusions-and","title":"Emergence and dynamics of delusions and hallucinations across stages in early psychosis","date":"2024-02-20","arxiv_id":"2402.13428","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-hallucination-detection-in-neural","title":"Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation","date":"2024-02-20","arxiv_id":"2402.13331","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-towards-domain-generalized-orientated","title":"GOOD: Towards Domain Generalized Orientated Object Detection","date":"2024-02-20","arxiv_id":"2402.12765","repositories_listed":0,"syntology":null}],"record_sha256":"a0bb86a0f3c90a0d46dee00c79a6b5694322badbaa76daa8ab500264762ec390","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}