English
Related papers

Related papers: Where Knowledge Collides: A Mechanistic Study of I…

200 papers

Integrating external knowledge into large language models (LLMs) presents a promising solution to overcome the limitations imposed by their antiquated and static parametric memory. Prior studies, however, have tended to over-reliance on…

Computation and Language · Computer Science 2024-05-30 Hao Zhang , Yuyang Zhang , Xiaoguang Li , Wenxuan Shi , Haonan Xu , Huanshuo Liu , Yasheng Wang , Lifeng Shang , Qun Liu , Yong Liu , Ruiming Tang

Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence,…

Computation and Language · Computer Science 2026-04-21 Minsung Kim , Dong-Kyum Kim , Jea Kwon , Nakyeong Yang , Kyomin Jung , Meeyoung Cha

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Computation and Language · Computer Science 2026-02-26 Pierre Beckmann , Matthieu Queloz

Large Multimodal Models(LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation(RAG) frameworks where the contextual information from external sources may contradict…

Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing external context. However, internal memory and external context…

Computation and Language · Computer Science 2024-02-29 Zhuoran Jin , Pengfei Cao , Hongbang Yuan , Yubo Chen , Jiexin Xu , Huaijun Li , Xiaojian Jiang , Kang Liu , Jun Zhao

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Computation and Language · Computer Science 2025-02-25 Moritz Miller , Kumar Shridhar

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Computation and Language · Computer Science 2025-04-01 Yihuai Hong , Dian Zhou , Meng Cao , Lei Yu , Zhijing Jin

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge,…

Computation and Language · Computer Science 2024-03-05 Tianjie Ju , Weiwei Sun , Wei Du , Xinwei Yuan , Zhaochun Ren , Gongshen Liu

Vision-language models (VLMs) increasingly combine visual and textual information to perform complex tasks. However, conflicts between their internal knowledge and external visual input can lead to hallucinations and unreliable predictions.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Francesco Ortu , Zhijing Jin , Diego Doimo , Alberto Cazzaniga

Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context. Existing methods…

Computation and Language · Computer Science 2026-05-13 Yigeng Zhou , Wu Li , Yifan Lu , Yequan Wang , Xuebo Liu , Wenya Wang , Jun Yu , Min Zhang , Jing Li

Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time. To understand how models use these sources together, we formalize the problem of…

Computation and Language · Computer Science 2022-01-13 Shayne Longpre , Kartik Perisetla , Anthony Chen , Nikhil Ramesh , Chris DuBois , Sameer Singh

Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to…

Computation and Language · Computer Science 2024-04-05 Yantao Liu , Zijun Yao , Xin Lv , Yuchen Fan , Shulin Cao , Jifan Yu , Lei Hou , Juanzi Li

Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context -- this phenomenon, known as…

Computation and Language · Computer Science 2025-02-11 Yu Zhao , Alessio Devoto , Giwon Hong , Xiaotang Du , Aryo Pradipta Gema , Hongru Wang , Xuanli He , Kam-Fai Wong , Pasquale Minervini

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

Computation and Language · Computer Science 2025-06-10 Atahan Özer , Çağatay Yıldız

Pre-trained language models (LMs) have been shown to memorize a substantial amount of knowledge from the pre-training corpora; however, they are still limited in recalling factually correct knowledge given a certain context. Hence, they…

Computation and Language · Computer Science 2022-04-08 Ruibo Liu , Guoqing Zheng , Shashank Gupta , Radhika Gaonkar , Chongyang Gao , Soroush Vosoughi , Milad Shokouhi , Ahmed Hassan Awadallah

Large language models internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a crucial dilemma known…

Artificial Intelligence · Computer Science 2024-07-29 Xiaowei Yuan , Zhao Yang , Yequan Wang , Shengping Liu , Jun Zhao , Kang Liu

Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. However, in order to remain up-to-date and align with human instructions, LLMs inevitably require external knowledge during…

Computation and Language · Computer Science 2023-09-18 Cheng Qian , Xinran Zhao , Sherry Tongshuang Wu

Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the…

Computation and Language · Computer Science 2024-08-23 Zhaochen Su , Jun Zhang , Xiaoye Qu , Tong Zhu , Yanshu Li , Jiashuo Sun , Juntao Li , Min Zhang , Yu Cheng

Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated excellent multilingual capabilities, which can express the…

Computation and Language · Computer Science 2024-11-27 Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to…

Computation and Language · Computer Science 2023-02-14 Adi Haviv , Ido Cohen , Jacob Gidron , Roei Schuster , Yoav Goldberg , Mor Geva