Hallucinations in medical conditions

Latest papers

• External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing

  Kingshuk Gupta, Davide Buscaldi · 2 October 2026

  As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability. While recent internal state probes offer a promising alternative to slow external retrieval systems, they largely reduce hallucination detection to a …

• Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data Splitting

  Chang Liu, Yu Tian, Rui Xie · 1 October 2026

  Multiple object hallucination, where large vision-language models (LVLMs) generate objects not supported by the visual input, is a persistent challenge caused by visual uncertainty during decoding. Existing methods reduce hallucinations using contrastive signals, but they rely on heuristics and lack…

• MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World Models

  Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar · 1 October 2026

  World Models are appearing as the next major frontier in computer vision. However, their robustness is currently largely unexplored. We identify the phenomenon of hallucination in latent World Models: given a state and an action, the predicted next latent can decode to a scene that never occurs. Bec…

• The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models

  Pranav Darshan, Pranav A, Sravan Karthick T, Minal Moharir, Ivan P. Yamshchikov · 30 September 2026

  Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable. This work studies that heterogeneity across four language models and three factual question answering datasets. Partitioning hallucinati…

• Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency

  Wenhan Yu, Wenxin Wu, Hao Wang, Lei Sha · 21 September 2026

  Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a factual question correctly in its original form but generates an incorrect answer under a semantically equivalent paraphrase. Such inconsistencies expo…

• NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass

  Ali Derogar Odolou, Reza Nazari, Mostafa Salehi · 15 September 2026

  Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to detect patterns of truthfulness and factuality. A less-studied approach is to identify feed-forward neurons correlated with hallucination. We propose a…

• HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA

  Syed Mohaiminul Hoque, Md Sakhawat Hossain · 11 September 2026

  Large multimodal models tend to hallucinate visual detail fluently, which limits their deployment for fine-grained interpretation. We present HALDETECT, our system for the English hallucination-detection track (Task 1b) of ImageEval 2026, in which a system must identify, from an image and three cult…

• Domain-Specific Hallucination Detection in Large Language Models

  Varun Teja Chundru, Debasmita Biswas · 11 September 2026

  Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration f…

• OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models

  Jianjiang Yang, Peihang Li, Shanqing Xu, Mengchen Qian, Lu Zhang, Meng Luo · 11 September 2026

  While Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse tasks, they suffer from hallucinations where generated outputs contradict or misrepresent input semantics. Existing research typically addresses hallucination detection within a single modality or task ty…

• MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

  Meng'en Qin, Junye Chen, Jucheng Liu, Youlu Xing, Song Wang, Ruize Han · 10 September 2026

  Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-based mitigation methods mainly rely on indirect signals (e.g., attention weights) that fail to accurately reflect the actual information shift underl…

• Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

  Renato Vukovic, Hsien-chin Lin, Carel van Niekerk, Benjamin Ruppik, Michael Heck, Shutong Feng, Nurul Lubis, Milica Gasic · 7 September 2026

  Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompted and fine-tuned language models. Detecting hallucinations is difficult due to the opaque reasoning processes of LLMs, which often provide little insi…

• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention

  Naveen Lamba, Sanju Tiwari, Manas Gaur · 28 August 2026

  The lifecycle of hallucination in LLMs is a concept that enables building solid frameworks on the control and reliability of LLMs in high-stakes environments, including health, legal, and scientific research. Although previous surveys have primarily focused on detection or mitigation, this survey pr…

• Do Large Language Models Hallucinate Electric Fata Morganas?

  Kristina \v{S}ekrst · 20 August 2026

  AI hallucinations - that is, outputs which are made up, cannot be verified, or contradict the source material - are generally regarded as an engineering flaw to be dealt with. This paper contends that they also have philosophical significance when it comes to the question of machine consciousness. W…

• Temporal Multi-Signal Fusion for Token-Level Hallucination Detection

  Igor Itkin · 20 August 2026

  Token-level hallucination detectors score each token independently from a single signal, and fail exactly when the generating model is confidently wrong. This paper instead treats hallucination as a temporally extended span and detects it by sequence labeling: each token is scored from a 33-dimensio…

• Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals

  Joao Fonseca, Rodrigo Rodrigues, Paolo Romano · 19 August 2026

  Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as hallucinations. Most existing detection methods operate at the answer or sentence level, yet per-token detection is essential for localizing hal…

• The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines

  Prabhjot Singh, Bhushan Pawar · 18 August 2026

  Sequential multi-agent LLM pipelines chain specialized agents without verification at handoffs, creating a structural flaw with measurable and severe consequences. We show that hallucinations injected at Stage 1 do not merely persist; they transform: raw numerical facts become derived computations, …

• Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness

  Srijith Ravikumar · 12 August 2026

  LLM recommenders for top-$K$ item suggestion regularly emit titles outside the target catalog. Prior audits measure this as a binary out-of-domain rate; none ask whether the model knew it was hallucinating. We jointly audit hallucination rate (OOD@10) and verbalized-confidence calibration (ECE, Brie…

• Unified Hallucination Fuzzing for Multimodal Large Language Models

  Pengfei Zhou, Jiajun Song, Zhiwei Tang, Yixing Ma, Xiaopeng Peng, Donghui Si, Yuhang Xu, Huiqi Song, Yiyuan Miao, Yichen Qian, Weihua Chen, Wangbo Zhao, Bohan Zhuang, Jiasheng Tang, Yang You · 11 August 2026

  Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications. Existing evaluations, predominantly based on static benchmarks, suffer from narrow taxonomical coverage and rapid performance saturation, failin…

• Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking

  Timothee Mickus, Claudio Savelli, Eduardo Cal\`o, Emilio Raimond, Stella Frank, Hengyu Luo, Flavio Giobergia, Vincent Segonne, Chuyuan Li, Aman Sinha, Lorenzo Vaiani, J\"org Tiedemann, Ra\'ul V\'azquez · 4 August 2026

  In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples could take the place of model-generated hallucinations, in order to make benchmarking detection independent of particular models. To this end, we construc…

• When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration

  Kesheng Chen, Yamin Hu, Wenjian Luo · 3 August 2026

  In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state. For example, a model may report that a visibly six-fingered hand has five fingers. We show that these errors are systematically directed: w…

• The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards

  Keyu Li, Jin Gao, Dequan Wang · 30 July 2026

  On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is toward how much compute that factuality costs. Static leaderboards score factuality in isolation and treat compute as free, so they cannot tell a genui…

• Rethinking CD: A Reproducibility Study and Extension on the Ineffectiveness of Contrastive Decoding at Mitigating Object Hallucinations in MLLMs

  Arnav Bendre, Guneesh Gupta, Kavish Grover, Chayan Aggarwal, Shreyansh Modi · 29 July 2026

  Contrastive decoding (CD) has been proposed as a training-free strategy for mitigating object hallucinations in multimodal large language models (MLLMs), with reported gains on benchmarks such as POPE. However, recent work has questioned whether these gains reflect genuine improvements in visual gro…

• Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection

  Yihao Xue, Kristjan Greenewald, Youssef Mroueh, Baharan Mirzasoleiman · 1 July 2026

  Large Language Models (LLMs) often hallucinate, limiting their reliability in sensitive applications. In black-box settings, several self-consistency-based techniques have been proposed for hallucination detection. We empirically show that these methods perform nearly as well as a supervised (black-…

• Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens

  Meng Shen, Minghao Wu, Deepu Rajan · 21 May 2026

  Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation over meaningful interaction with images. To explore this, w…

• MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs

  Wei Ding, Yilin Li, Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Yu Wang · 15 May 2026

  Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinations, generating content that is inconsistent with the visual input. Prior work DHCP (Detecting Hallucinations by Cross-modal Attention Pattern) has e…