English
Related papers

Related papers: DOPRA: Decoding Over-accumulation Penalization and…

200 papers

Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously acquired reasoning abilities. This tension reflects a…

Artificial Intelligence · Computer Science 2026-05-26 Mustafa Hayri Bilgin , Mariam Barry , Albert Bifet , Azzedine Idir Ait Said , Soumya Banerjee

Large Language Models (LLMs) demonstrate remarkable capabilities in text understanding and generation. However, their tendency to produce factually inconsistent outputs, commonly referred to as ''hallucinations'', remains a critical…

Computation and Language · Computer Science 2026-01-13 Dingwei Chen , Ziqiang Liu , Feiteng Fang , Chak Tou Leong , Shiwen Ni , Ahmadreza Argha , Hamid Alinejad-Rokny , Min Yang , Chengming Li

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

Computation and Language · Computer Science 2025-10-15 Yukun Zhang , Qi Dong

Inference time scaling drives extended reasoning to enhance the performance of Vision-Language Models (VLMs), thus forming powerful Vision-Language Reasoning Models (VLRMs). However, long reasoning dilutes visual tokens, causing visual…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Xu Chu , Xinrong Chen , Guanyu Wang , Zhijie Tan , Kui Huang , Wenyu Lv , Tong Mo , Weiping Li

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Jiaqi Wang , Yifei Gao , Jitao Sang

Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem by comparing predictions from the original image with those…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Tian Qin , Junzhe Chen , Yuqing Shi , Tianshu Zhang , Qiang Ju , Lijie Wen

Large language models (LLMs) have shown promise for generative and knowledge-intensive tasks including question-answering (QA) tasks. However, the practical deployment still faces challenges, notably the issue of "hallucination", where…

Computation and Language · Computer Science 2023-10-11 Ziwei Ji , Tiezheng Yu , Yan Xu , Nayeon Lee , Etsuko Ishii , Pascale Fung

The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limited research to explore the relationship between image tokens…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Xiaofeng Zhang , Yihao Quan , Chaochen Gu , Chen Shen , Xiaosong Yuan , Shaotian Yan , Hao Cheng , Kaijie Wu , Jieping Ye

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit…

Computation and Language · Computer Science 2024-07-25 Georgios Kollias , Payel Das , Subhajit Chaudhury

Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and…

Computation and Language · Computer Science 2026-04-15 Sihang Jia , Shuliang Liu , Songbo Yang , Yibo Yan , Xin Zou , Xuming Hu

While Multimodal Large Language Models (MLLMs) excel at generalizing across modalities and tasks, effectively adapting them to specific downstream tasks while simultaneously retaining both general and specialized knowledge remains…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Jian Liang , Wenke Huang , Guancheng Wan , Qu Yang , Mang Ye

Large language model hallucination represents a critical challenge where outputs deviate from factual accuracy due to distributional biases in training data. While recent investigations establish that specific hidden layers exhibit…

Computation and Language · Computer Science 2025-09-29 Wenkai Wang , Vincent Lee , Yizhen Zheng

This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of…

Computation and Language · Computer Science 2025-01-14 Jordan Meadows , Marco Valentino , Andre Freitas

We investigate the internal structure of language model computations using causal analysis and demonstrate two motifs: (1) a form of adaptive computation where ablations of one attention layer of a language model cause another layer to…

Machine Learning · Computer Science 2023-08-01 Thomas McGrath , Matthew Rahtz , Janos Kramar , Vladimir Mikulik , Shane Legg

Large language models (LLMs) exhibit remarkable capabilities in natural language processing but face catastrophic forgetting when learning new tasks, where adaptation to a new domain leads to a substantial decline in performance on previous…

Computation and Language · Computer Science 2025-03-24 Yuheng Lu , Bingshuo Qian , Caixia Yuan , Huixing Jiang , Xiaojie Wang

Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization, achieving impressive capabilities across various challenging benchmarks. However, our empirical analysis reveals a…

Computation and Language · Computer Science 2025-11-07 Junyi Li , Hwee Tou Ng

In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that at times, introducing hallucinations is necessary to…

Image and Video Processing · Electrical Eng. & Systems 2025-03-07 Till Aczel , Roger Wattenhofer

While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually incorrect contents. Existing methods to mitigating such risk…

Computation and Language · Computer Science 2025-09-16 Yurui Chang , Bochuan Cao , Lu Lin

Low-Rank Adaptation (LoRA) has emerged as an effective technique for reducing memory overhead in fine-tuning large language models. However, it often suffers from sub-optimal performance compared with full fine-tuning since the update is…

Machine Learning · Computer Science 2025-09-30 Xin Yu , Yujia Wang , Jinghui Chen , Lingzhou Xue

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zixian Gao , Chao Yang , Zhanhui Zhou , Xing Xu , Chaochao Lu