English
Related papers

Related papers: From Prerequisites to Predictions: Validating a Ge…

200 papers

Deploying autonomous agents in the wild requires reliable safeguards against tool use failures. We propose a training free guardrail based on spectral analysis of attention topology that complements supervised approaches. On Llama 3.1 8B,…

Machine Learning · Computer Science 2026-02-10 Valentin Noël

Concept probes extracted from transformer residual streams are only as reliable as the layer from which they are extracted. The common practice of probing at a fixed late layer or at the peak of a separation score function ignores a…

Machine Learning · Computer Science 2026-05-26 James Henry

Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information. In this paper, we systematically study the object hallucination problem from three…

Computation and Language · Computer Science 2023-02-13 Wenliang Dai , Zihan Liu , Ziwei Ji , Dan Su , Pascale Fung

Retrieval-Augmented Generation (RAG) models are designed to incorporate external knowledge, reducing hallucinations caused by insufficient parametric (internal) knowledge. However, even with accurate and relevant retrieved content, RAG…

Computation and Language · Computer Science 2025-01-22 Zhongxiang Sun , Xiaoxue Zang , Kai Zheng , Yang Song , Jun Xu , Xiao Zhang , Weijie Yu , Yang Song , Han Li

Large language models (LLMs) produce systematically misleading outputs, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by separate communities with incompatible terminology. We propose a…

Computers and Society · Computer Science 2026-04-07 Jerick Shi , Terry Jingcheng Zhang , Zhijing Jin , Vincent Conitzer

Twisting symmetries provides an efficient method to diagnose symmetry-protected topological (SPT) phases. In this paper, edge theories of (2+1)-dimensional topological phases protected by reflection as well as other symmetries are studied…

Strongly Correlated Electrons · Physics 2015-06-03 Gil Young Cho , Chang-Tse Hsieh , Takahiro Morimoto , Shinsei Ryu

While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in open-ended visual question answering, they remain vulnerable to hallucinations. These are outputs that contradict or misrepresent input semantics, posing a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jianjiang Yang , Yanshu li , Ziyan Huang

Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their…

Computation and Language · Computer Science 2024-08-20 Yakir Yehuda , Itzik Malkiel , Oren Barkan , Jonathan Weill , Royi Ronen , Noam Koenigstein

In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside…

Computation and Language · Computer Science 2024-08-21 Ameya Godbole , Nicholas Monath , Seungyeon Kim , Ankit Singh Rawat , Andrew McCallum , Manzil Zaheer

Geometric foundation models hold promise for unconstrained dense geometry prediction from uncalibrated images. However, in current feed-forward designs, their predicted confidence scores are heuristic, lack probabilistic interpretation, and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zihao Zhu , Wenyuan Zhao , Nuo Chen , Chao Tian , Zhiwen Fan

In language and vision-language models, hallucination is broadly understood as content generated from a model's prior knowledge or biases rather than from the given input. While this phenomenon has been studied in those domains, it has not…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Seyed Amir Kasaei , Mohammad Hossein Rohban

AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, such hallucinations are not equally problematic: some hallucination contents could be…

Artificial Intelligence · Computer Science 2026-04-09 Jianhong Pang , Ruoxi Cheng , Ziyi Ye , Xingjun Ma , Zuxuan Wu , Xuanjing Huang , Yu-Gang Jiang

Single-pass hallucination detectors rely on internal telemetry (e.g., uncertainty, hidden-state geometry, and attention) of large language models, implicitly assuming hallucinations leave separable traces in these signals. We study a…

Cryptography and Security · Computer Science 2026-01-22 Nay Myat Min , Long H. Pham , Hongyu Zhang , Jun Sun

Recent methodologies utilizing synthetic datasets have aimed to address inconsistent hallucinations in large language models (LLMs); however,these approaches are primarily tailored to specific tasks, limiting their generalizability.…

Artificial Intelligence · Computer Science 2025-02-28 Xinxin You , Xien Liu , Qixin Sun , Huan Zhang , Kaiyin Zhou , Shaohui Liu , GuoPing Hu , ShiJin Wang , Si Liu , Ji Wu

Large language models can follow complex procedures yet fail at a seemingly trivial final step: reporting a value they themselves computed moments earlier. We study this phenomenon as \emph{procedural hallucination}: failure to execute a…

Machine Learning · Statistics 2026-02-24 Ahmed Karim , Fatima Sheaib , Zein Khamis , Maggie Chlon , Jad Awada , Leon Chlon

LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper…

Artificial Intelligence · Computer Science 2026-05-27 Paul Sigloch , Christoph Benzmüller

Hallucinations of vision-language models (VLMs), which are misalignments between visual content and generated text, undermine the reliability of VLMs. One common approach for detecting them employs the same VLM, or a different one, to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Ofir Azachi , Kfir Eliyahu , Eyal El Ani , Rom Himelstein , Roi Reichart , Yuval Pinter , Nitay Calderon

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…

Machine Learning · Computer Science 2026-02-09 Long Zhang , Fangwei Lin

Financial AI systems must produce answers grounded in specific regulatory filings, yet current LLMs fabricate metrics, invent citations, and miscalculate derived quantities. These errors carry direct regulatory consequences as the EU AI…

Artificial Intelligence · Computer Science 2026-04-28 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do…

Computation and Language · Computer Science 2024-09-04 Spencer Whitehead , Jacob Phillips , Sean Hendryx