English
Related papers

Related papers: MoRFI: Monotonic Sparse Autoencoder Feature Identi…

200 papers

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Artificial Intelligence · Computer Science 2026-01-23 Manish Bhatt

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Machine Learning · Computer Science 2025-08-14 Charles O'Neill , Mudith Jayasekara , Max Kirkby

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Computation and Language · Computer Science 2025-06-04 Shota Takashiro , Takeshi Kojima , Andrew Gambardella , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Kassoum Sanogo , Renzo Ardiccioni

Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task. However, effective strategies for fine-tuning LLMs for the QA task…

Computation and Language · Computer Science 2025-01-22 Junjie Ye , Yuming Yang , Qi Zhang , Tao Gui , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Renjie Pi , Kehao Miao , Li Peihang , Runtao Liu , Jiahui Gao , Jipeng Zhang , Xiaofang Zhou

Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains questionable. In this paper, we identify a critical failure…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Zhihao Zhu , Jiafeng Liang , Shixin Jiang , Jinlan Fu , Ming Liu , Guanglu Sun , See-Kiong Ng , Bing Qin

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representation methods for hallucination detection, most of these…

Machine Learning · Computer Science 2025-11-17 Elyes Hajji , Aymen Bouguerra , Fabio Arnez

We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (SAE) features collected from just a handful of prompts. Focusing on concept-relation…

Computation and Language · Computer Science 2026-04-21 Ruixuan Deng , Xiaoyang Hu , Miles Gilberti , Shane Storks , Aman Taxali , Mike Angstadt , Chandra Sripada , Joyce Chai

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Zhiyang Chen , Yousong Zhu , Yufei Zhan , Zhaowen Li , Chaoyang Zhao , Jinqiao Wang , Ming Tang

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise…

Computation and Language · Computer Science 2025-05-28 Boyi Deng , Yu Wan , Yidan Zhang , Baosong Yang , Fuli Feng

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…

Computation and Language · Computer Science 2024-05-31 Ernesto Quevedo , Jorge Yero , Rachel Koerner , Pablo Rivas , Tomas Cerny

The widespread adoption and transformative effects of large language models (LLMs) have sparked concerns regarding their capacity to produce inaccurate and fictitious content, referred to as `hallucinations'. Given the potential risks…

Human-Computer Interaction · Computer Science 2024-08-13 Mahjabin Nahar , Haeseung Seo , Eun-Ju Lee , Aiping Xiong , Dongwon Lee

Large language models (LLMs) excel in speed and adaptability across various reasoning tasks, but they often struggle when strict logic or constraint enforcement is required. In contrast, Large Reasoning Models (LRMs) are specifically…

Large Language Models (LLMs) frequently exhibit unfaithful behavior, producing a final answer that differs significantly from their internal chain of thought (CoT) reasoning in order to appease the user they are conversing with. In order to…

Computation and Language · Computer Science 2026-02-04 Shikhar Shiromani , Archie Chaudhury , Sri Pranav Kunda

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability. This paper aims to study the hallucination problem of LMMs in video…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Hongcheng Gao , Jiashu Qu , Jingyi Tang , Baolong Bi , Yue Liu , Hongyu Chen , Li Liang , Li Su , Qingming Huang

Although Large Vision-Language Models (LVLMs) have made substantial progress, hallucination, where generated text is not grounded in the visual input, remains a challenge. As LVLMs become stronger, previously reported hallucination…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 April Fu