English
Related papers

Related papers: COPO: Causal-Oriented Policy Optimization for Hall…

200 papers

Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) by learning from preference pairs. One of its key challenges lies in how to transfer the…

Machine Learning · Computer Science 2026-05-07 Huatian Zhang , Zhendong Mao , Lei Zhang , Yongdong Zhang

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Wenhao Yang , Yu Xia , Jinlong Huang , Shiyin Lu , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Yuchen Zhou , Xiaobo Xia , Yuanyu Wan , Lijun Zhang , Tat-Seng Chua

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent…

Artificial Intelligence · Computer Science 2025-05-27 Xinmiao Hu , Chun Wang , Ruihe An , ChenYu Shao , Xiaojun Ye , Sheng Zhou , Liangcheng Li

Multimodal Large Language Models (MLLMs) often suffer from hallucinations, particularly errors in object existence, attributes, or relations, which undermine their reliability. We introduce TACO (Verified Atomic Confidence Estimation), a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Jiarui Liu , Weihao Xuan , Zhijing Jin , Mona Diab

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as…

Artificial Intelligence · Computer Science 2025-12-04 Boyang Gu , Hongjian Zhou , Bradley Max Segal , Jinge Wu , Zeyu Cao , Hantao Zhong , Lei Clifton , Fenglin Liu , David A. Clifton

Direct Preference Optimization (DPO) is a powerful paradigm for aligning Large Language Models (LLMs) to human preferences in Machine Translation (MT), but current methods are hindered by two fundamental challenges: (1) flawed reward…

Computation and Language · Computer Science 2025-10-16 Hao Wang , Linlong Xu , Heng Liu , Yangyang Liu , Xiaohu Zhao , Bo Zeng , Liangying Shao , Longyue Wang , Weihua Luo , Kaifu Zhang

Memory-augmented LLM agents tackle complex long-horizon tasks by recursively summarizing interaction trajectories into compact memory. However, existing approaches typically train these memory policies using outcome-based reinforcement…

Artificial Intelligence · Computer Science 2026-05-29 Ziyan Liu , Zhezheng Hao , Yeqiu Chen , Hong Wang , Jingren Hou , Ruiyi Ding , Yongkang Yang , Wence Ji , Wei Xia , Feng Liu

Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Qidong Huang , Xiaoyi Dong , Pan Zhang , Bin Wang , Conghui He , Jiaqi Wang , Dahua Lin , Weiming Zhang , Nenghai Yu

We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision--language models (VLMs). Reliable perception is a core requirement for VLM-based agents that must reason and act in open-ended environments: faulty…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Ahmad Rezaei , Mohsen Gholami , Saeed Ranjbar Alvar , Kevin Cannons , Mohammad Asiful Hossain , Zhou Weimin , Yong Zhang , Mohammad Akbari

Audio and omni-modal large language models exhibit impressive cross-modal reasoning capabilities. However, applying standard reinforcement learning post-training algorithms to these models exposes a critical structural vulnerability:…

Computation and Language · Computer Science 2026-05-28 Cihan Xiao , Yiwen Shao , Chenxing Li , Xiang He , Zhenwen Liang , Steve Yves , Sanjeev Khudanpur , Liefeng Bo

Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding is disproportionately drawn to visually dominant or frequently occurring content. We…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Mohammad Anas Azeez , Ankan Deria , Zohaib Hasan Siddiqui , Adinath Madhavrao Dukre , Rafiq Ali , Sara Atito , Yutong Xie , Imran Razzak

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Xiaochen Yang , Hao Fang , Jiawei Kong , Yaoxin Mao , Bin Chen , Shu-Tao Xia

Large language models (LLMs) can be prone to hallucinations - generating unreliable outputs that are unfaithful to their inputs, external facts or internally inconsistent. In this work, we address several challenges for post-hoc…

Computation and Language · Computer Science 2024-08-12 Simon Valentin , Jinmiao Fu , Gianluca Detommaso , Shaoyuan Xu , Giovanni Zappella , Bryan Wang

Large Language Models (LLMs) in multi-turn conversations often suffer from a ``lost-in-conversation'' phenomenon, where they struggle to recover from early incorrect assumptions, particularly when users provide ambiguous initial…

Computation and Language · Computer Science 2026-01-23 Zhebo Wang , Xiaohu Mu , Zijie Zhou , Mohan Li , Wenpeng Xing , Dezhang Kong , Meng Han

Although multimodal large language models (MLLMs) exhibit remarkable reasoning capabilities on complex multimodal understanding tasks, they still suffer from the notorious hallucination issue: generating outputs misaligned with obvious…

Machine Learning · Computer Science 2025-11-04 Wei Chen , Xin Yan , Bin Wen , Fan Yang , Tingting Gao , Di Zhang , Long Chen

Preference alignment methods such as RLHF and Direct Preference Optimization (DPO) improve instruction following, but they can also reinforce hallucinations when preference judgments reward fluency and confidence over factual correctness.…

Computation and Language · Computer Science 2026-04-16 Sindhuja Chaduvula , Ahmed Y. Radwan , Azib Farooq , Yani Ioannou , Shaina Raza

This paper presents a new optimization approach to causal estimation. Given data that contains covariates and an outcome, which covariates are causes of the outcome, and what is the strength of the causality? In classical machine learning…

Methodology · Statistics 2024-10-22 Mingzhang Yin , Yixin Wang , David M. Blei

Despite the rapid success of Large Vision-Language Models (LVLMs), a persistent challenge is their tendency to generate hallucinated content, undermining reliability in real-world use. Existing training-free methods address hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Neeraj Anand , Samyak Jha , Udbhav Bamba , Rahul Rahaman

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance…

Computation and Language · Computer Science 2024-08-12 Avshalom Manevich , Reut Tsarfaty

Bias in Large Language Models (LLMs) poses significant risks to trustworthiness, manifesting primarily as stereotypical biases (e.g., gender or racial stereotypes) and structural biases (e.g., lexical overlap or position preferences).…

Computation and Language · Computer Science 2025-12-30 Xuan Feng , Bo An , Tianlong Gu , Liang Chang , Fengrui Hao , Peipeng Yu , Shuai Zhao