English
Related papers

Related papers: REACT: Representation Extraction And Controllable …

200 papers

Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, detaching themselves from training. This separation introduces…

Machine Learning · Computer Science 2026-05-08 Wanru Zhao , Yihong Chen , Yuzhi Tang , Wentao Ma , Shengchao Hu , Shell Xu Hu , Alex Iacob , Abhinav Mehrotra , Nicholas D. Lane

Large language models (LLMs) excel at generating long-form responses, but evaluating their factuality remains challenging due to complex inter-sentence dependencies within the generated facts. Prior solutions predominantly follow a…

Computation and Language · Computer Science 2025-09-30 Xin Liu , Lechen Zhang , Sheza Munir , Yiyang Gu , Lu Wang

Large language models (LLMs) can generate long-form and coherent text, yet they often hallucinate facts, which undermines their reliability. To mitigate this issue, inference-time methods steer LLM representations toward the "truthful…

Computation and Language · Computer Science 2024-06-10 Farima Fatahi Bayat , Xin Liu , H. V. Jagadish , Lu Wang

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

Artificial Intelligence · Computer Science 2026-03-10 Weize Liu , Minghui Liu , Sy-Tuyen Ho , Souradip Chakraborty , Xiyao Wang , Furong Huang

Relational fact extraction aims to extract semantic triplets from unstructured text. In this work, we show that all of the relational fact extraction models can be organized according to a graph-oriented analytical perspective. An efficient…

Computation and Language · Computer Science 2021-06-04 Fubang Zhao , Zhuoren Jiang , Yangyang Kang , Changlong Sun , Xiaozhong Liu

The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known as chain-of-thought (CoT). However, CoT often becomes…

Computation and Language · Computer Science 2026-01-07 Nathanaël Carraz Rakotonirina , Ren Pang , Neha Anna John , Michael Bohlke-Schneider , Momchil Hardalov

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual…

Current approaches of knowledge editing struggle to effectively propagate updates to interconnected facts. In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within these models for…

Computation and Language · Computer Science 2024-02-01 Wenyue Hua , Jiang Guo , Mingwen Dong , Henghui Zhu , Patrick Ng , Zhiguo Wang

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on…

Computation and Language · Computer Science 2026-05-12 Chi Zhang , Mengqi Zhang , Xiaotian Ye , Runxi Cheng , Zisheng Zhou , Ying Zhou , Pengjie Ren , Zhumin Chen

Recently, large language models (LLMs) have demonstrated outstanding reasoning capabilities on mathematical and coding tasks. However, their application to financial tasks-especially the most fundamental task of stock movement…

Computation and Language · Computer Science 2025-10-27 Xueyuan Lin , Cehao Yang , Ye Ma , Ming Li , Rongjunchen Zhang , Yang Ni , Xiaojun Wu , Chengjin Xu , Jian Guo , Hui Xiong

Knowledge editing methods such as ROME and MEMIT update factual associations in transformer models by modifying MLP weights. While evaluated mainly by output behavior, their internal mechanism remains underexplored. We investigate whether…

Machine Learning · Computer Science 2026-05-29 Ali Holmov , Paul Youssef , Nandi Schoots , Christin Seifert

Safety alignment is crucial for large language models (LLMs) to resist malicious instructions but often results in over-refusals, where benign prompts are unnecessarily rejected, impairing user experience and model utility. We introduce…

Machine Learning · Computer Science 2025-07-08 Mahavir Dabas , Si Chen , Charles Fleming , Ming Jin , Ruoxi Jia

Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have become the standard paradigm, the mechanisms underlying how…

Computation and Language · Computer Science 2026-05-12 Haoyu Wang , Yifan Shang , Zhongxiang Sun , Weijie Yu , Xiao Zhang , Jun Xu

Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a discussion. Comparing human to LLM-generated edits, however, we observe a mismatch in…

Computation and Language · Computer Science 2026-04-15 Timon Ziegenbein , Maja Stahl , Henning Wachsmuth

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations. However,…

Computation and Language · Computer Science 2026-04-16 Aleksandr Rubashevskii , Dzianis Piatrashyn , Preslav Nakov , Maxim Panov

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…

Machine Learning · Computer Science 2025-09-23 Shuhao Jiang , Songbo Wang , Yang Qiao , Chun Xu , Chaoyang Zheng , Shengyi Zhou , Huanjun Wang , Fangming Li , Cong Zhang , Jiyu Wang

Model editing aims at selectively updating a small subset of a neural model's parameters with an interpretable strategy to achieve desired modifications. It can significantly reduce computational costs to adapt to large language models…

Computation and Language · Computer Science 2025-03-20 Shichen Li , Zhongqing Wang , Zheyu Zhao , Yue Zhang , Peifeng Li

Memory-efficient large language models are good at refining text input for better readability. However, controllability is a matter of concern when it comes to text generation tasks with long inputs, such as multi-document summarization. In…

Computation and Language · Computer Science 2023-10-06 Litton J Kurisinkel , Nancy F chen

Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a…

Computation and Language · Computer Science 2025-02-11 Paul Youssef , Zhixue Zhao , Christin Seifert , Jörg Schlötterer

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Machine Learning · Computer Science 2025-10-03 Aniket Vashishtha , Qirun Dai , Hongyuan Mei , Amit Sharma , Chenhao Tan , Hao Peng