English
Related papers

Related papers: Mechanistic Circuit-Based Knowledge Editing in Lar…

200 papers

In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have…

Artificial Intelligence · Computer Science 2025-03-18 Hang Luo , Jian Zhang , Chujun Li

Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-based MRC, where the passages are multi-turn dialogues. It…

Computation and Language · Computer Science 2020-09-11 Junlong Li , Zhuosheng Zhang , Hai Zhao

An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external…

Computation and Language · Computer Science 2024-04-03 Xin Su , Tiep Le , Steven Bethard , Phillip Howard

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning…

Computation and Language · Computer Science 2024-10-18 Minseok Choi , ChaeHun Park , Dohyun Lee , Jaegul Choo

The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundaries of this reasoning capability. However, tasks that embody…

Artificial Intelligence · Computer Science 2025-02-27 Yuze Zhao , Tianyun Ji , Wenjun Feng , Zhenya Huang , Qi Liu , Zhiding Liu , Yixiao Ma , Kai Zhang , Enhong Chen

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

Computation and Language · Computer Science 2026-02-11 Yisu Wang , Ming Wang , Haoyuan Song , Wenjie Huang , Chaozheng Wang , Yi Xie , Xuming Ran

Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most existing methods focus…

Computation and Language · Computer Science 2025-11-03 Jiahao Liu , Zijian Wang , Kuo Zhao , Dong Hu

Instruction-based image editing (IIE) has advanced rapidly with the success of diffusion models. However, existing efforts primarily focus on simple and explicit instructions to execute editing operations such as adding, deleting, moving,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Qingdong He , Xueqin Chen , Chaoyi Wang , Yanjie Pan , Xiaobin Hu , Zhenye Gan , Yabiao Wang , Chengjie Wang , Xiangtai Li , Jiangning Zhang

Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these improve performance, they often reach a saturation point.…

Computation and Language · Computer Science 2025-09-18 Justin Chih-Yao Chen , Archiki Prasad , Swarnadeep Saha , Elias Stengel-Eskin , Mohit Bansal

Multi-hop questions still stump large language models (LLMs), which struggle to link information across multiple reasoning steps. We introduce Auto-Patch, a novel method that dynamically patches hidden states during inference to enhance…

Computation and Language · Computer Science 2025-06-03 Aviv Jan , Dean Tahory , Omer Talmi , Omar Abo Mokh

As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing outdated knowledge in…

Computation and Language · Computer Science 2024-09-17 Baolong Bi , Shenghua Liu , Yiwei Wang , Lingrui Mei , Hongcheng Gao , Junfeng Fang , Xueqi Cheng

Large Language Models (LLMs) suffer from a critical limitation: their knowledge is static and quickly becomes outdated. Retraining these massive models is computationally prohibitive, while existing knowledge editing techniques can be slow…

Computation and Language · Computer Science 2025-12-30 Kabir Khan , Priya Sharma , Arjun Mehta , Neha Gupta , Ravi Narayanan

Large language models (LLMs) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hypothesis}, suggesting that bridge entities are computed…

Computation and Language · Computer Science 2026-01-08 Xukai Liu , Ye Liu , Jipeng Zhang , Yanghai Zhang , Kai Zhang , Qi Liu

As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing…

Computation and Language · Computer Science 2024-12-31 Yongchang Li , Yujin Zhu , Tao Yan , Shijian Fan , Gang Wu , Liang Xu

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability…

Computation and Language · Computer Science 2024-04-30 Ningyu Zhang , Bozhong Tian , Siyuan Cheng , Xiaozhuan Liang , Yi Hu , Kouying Xue , Yanjie Gou , Xi Chen , Huajun Chen

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Artificial Intelligence · Computer Science 2026-03-24 Zhuojie Yang , Wentao Wan , Keze Wang

Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured…

Computation and Language · Computer Science 2025-07-08 Swayamjit Saha

LLMs are widely used in knowledge-intensive tasks where the same fact may be revised multiple times within context. Unlike prior work focusing on one-shot updates or single conflicts, multi-update scenarios contain multiple historically…

Computation and Language · Computer Science 2026-03-16 Boyu Qiao , Sean Guo , Xian Yang , Kun Li , Wei Zhou , Songlin Hu , Yunya Song

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…

Machine Learning · Computer Science 2026-03-10 Antonio De Santis , Schrasing Tong , Marco Brambilla , Lalana Kagal

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversaries can inject malicious or misleading knowledge that corrupts…

Artificial Intelligence · Computer Science 2026-05-12 Qinghua Mao , Xi Lin , Jinze Gu , Jun Wu , Siyuan Li , Yuliang Chen