English
Related papers

Related papers: Where Does Reasoning Break? Step-Level Hallucinati…

200 papers

LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding significant latency and cost. We hypothesize that intermediate layers encode…

Computation and Language · Computer Science 2026-01-30 Rohan Bhatnagar , Youran Sun , Chi Andrew Zhang , Yixin Wen , Haizhao Yang

Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of efficient small models is essential to ensure low latency and…

Artificial Intelligence · Computer Science 2026-03-05 Zepeng Bao , Shen Zhou , Qiankun Pi , Jianhao Chen , Mayi Xu , Ming Zhong , Yuanyuan Zhu , Tieyun Qian

Large Language Models suffer from hallucination, generating plausible yet factually incorrect content. Current mitigation strategies focus on post-generation correction, which is computationally expensive and fails to prevent unreliable…

Computation and Language · Computer Science 2025-10-03 Nandakishor M

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Machine Learning · Computer Science 2025-10-23 Constantin Venhoff , Iván Arcuschin , Philip Torr , Arthur Conmy , Neel Nanda

Existing explainability methods for Large Language Models (LLMs) typically treat hidden states as static points in activation space, assuming that correct and incorrect inferences can be separated using representations from an individual…

Computation and Language · Computer Science 2026-03-03 Hamed Damirchi , Ignacio Meza De la Jara , Ehsan Abbasnejad , Afshar Shamsi , Zhen Zhang , Javen Shi

Large reasoning models (LRMs) that generate long chains of thought now perform well on multi-step math, science, and coding tasks. However, their behavior is still unstable and hard to interpret, and existing analysis tools struggle with…

Artificial Intelligence · Computer Science 2026-04-09 Xiaoyu Xu , Yulan Pan , Xiaosong Yuan , Zhihong Shen , Minghao Su , Yuanhao Su , Xiaofeng Zhang

While Test-Time Scaling (TTS) has proven effective in improving the reasoning ability of large language models (LLMs), low diversity in model outputs often becomes a bottleneck; this is partly caused by the common "one problem, one…

Computation and Language · Computer Science 2026-01-06 Feng Ju , Zeyu Qin , Rui Min , Zhitao He , Lingpeng Kong , Yi R. Fung

Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination detection, but their embeddings, optimized for linguistic…

Machine Learning · Computer Science 2025-05-23 Seongheon Park , Xuefeng Du , Min-Hsuan Yeh , Haobo Wang , Yixuan Li

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

Computation and Language · Computer Science 2026-05-15 Yumeng Zhang , Zhengbang Yang , Yevin Nikhel Goonatilake , Zhuangdi Zhu

Detecting hallucinations in large language models (LLMs) is critical for enhancing their reliability and trustworthiness. Most research focuses on hallucinations as deviations from information seen during training. However, the opaque…

Computation and Language · Computer Science 2025-03-26 Fabian Ridder , Malte Schilling

The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…

Artificial Intelligence · Computer Science 2025-10-02 Xiangyu Wen , Junhua Huang , Zeju Li , Min Li , Jianyuan Zhong , Zhijian Xu , Mingxuan Yuan , Yongxiang Huang , Qiang Xu

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

Computation and Language · Computer Science 2025-09-08 Adam Tauman Kalai , Ofir Nachum , Santosh S. Vempala , Edwin Zhang

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection…

Computation and Language · Computer Science 2025-12-25 Shize Liang , Hongzhi Wang

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

We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stability theory. Rather than treating hallucination as a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Bozhi Luan , Gen Li , Yalan Qin , Jifeng Guo , Yun Zhou , Faguo Wu , Hongwei Zheng , Wenjun Wu , Zhaoxin Fan

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

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Soumyadeep Jana , Pulkit Mittal , Sanasam Ranbir Singh

Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that incorporates mechanisms such as backtracking,…

Computation and Language · Computer Science 2025-10-21 Baohao Liao , Xinyi Chen , Sara Rajaee , Yuhui Xu , Christian Herold , Anders Søgaard , Maarten de Rijke , Christof Monz

Loss curves are smooth during most of model training, so visible discontinuities stand out as possible conceptual breakthroughs. Studying these breakthroughs enables a deeper understanding of learning dynamics, but only when they are…

Machine Learning · Computer Science 2026-03-23 Sara Kangaslahti , Elan Rosenfeld , Naomi Saphra

Large Vision-Language Models (LVLMs) face a tug-of-war between powerful linguistic priors and visual evidence, often leading to \emph{semantic drift}: a progressive detachment from the input image that can abruptly emerge at specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Jiahe Chen , Jiaying He , Qiyuan Chen , Qian Shao , Jiahe Ying , Hongxia Xu , Jintai Chen , Jianwei Zheng , Jian Wu