English
Related papers

Related papers: FaithSteer-BENCH: A Deployment-Aligned Stress-Test…

200 papers

Large language models (LLMs) excel at explicit reasoning, but their implicit computational strategies remain underexplored. Decades of psychophysics research show that humans intuitively process and integrate noisy signals using…

Computation and Language · Computer Science 2025-12-03 Julian Ma , Jun Wang , Zafeirios Fountas

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to overfitting and…

Machine Learning · Computer Science 2026-03-17 Yuntai Bao , Xuhong Zhang , Jintao Chen , Ge Su , Yuxiang Cai , Hao Peng , Bing Sun , Haiqin Weng , Liu Yan , Jianwei Yin

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Computation and Language · Computer Science 2025-06-30 Yichi Zhang , Siyuan Zhang , Yao Huang , Zeyu Xia , Zhengwei Fang , Xiao Yang , Ranjie Duan , Dong Yan , Yinpeng Dong , Jun Zhu

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…

Artificial Intelligence · Computer Science 2025-08-12 Changqing Li , Tianlin Li , Xiaohan Zhang , Aishan Liu , Li Pan

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

Computation and Language · Computer Science 2025-12-03 Lechen Zhang , Yusheng Zhou , Tolga Ergen , Lajanugen Logeswaran , Moontae Lee , David Jurgens

Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution capabilities. However, the field still lacks a high-quality and unified evaluation…

Artificial Intelligence · Computer Science 2026-05-12 Yize Li , Junzhi Li , Jason Song , Chuxiong Sun , Rui Wang , Changwen Zheng

The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on fragmented…

Computation and Language · Computer Science 2025-05-07 Tao Zhang , Chenglin Zhu , Yanjun Shen , Wenjing Luo , Yan Zhang , Hao Liang , Tao Zhang , Fan Yang , Mingan Lin , Yujing Qiao , Weipeng Chen , Bin Cui , Wentao Zhang , Zenan Zhou

Large language models (LLMs) are increasingly powering Text-to-SQL (Text2SQL) systems, enabling non-expert users to query industrial databases using natural language. While test-time scaling strategies have shown promise in LLM-based…

Computation and Language · Computer Science 2025-10-14 Jiajing Guo , Kenil Patel , Jorge Piazentin Ono , Wenbin He , Liu Ren

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

Computation and Language · Computer Science 2026-05-06 Geert Heyman , Frederik Vandeputte

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

Artificial Intelligence · Computer Science 2026-04-16 Chonghan Qin , Xiachong Feng , Weitao Ma , Xiaocheng Feng , Lingpeng Kong

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…

Machine Learning · Computer Science 2026-03-13 Eric Bigelow , Daniel Wurgaft , YingQiao Wang , Noah Goodman , Tomer Ullman , Hidenori Tanaka , Ekdeep Singh Lubana

We present Fusion Steering, an activation steering methodology that improves factual accuracy in large language models (LLMs) for question-answering (QA) tasks. This approach introduces flexible steering configurations, including full-layer…

Computation and Language · Computer Science 2025-05-29 Waldemar Chang , Alhassan Yasin

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Computation and Language · Computer Science 2025-10-07 Ken Tsui

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Xintong Zhang , Xiaowen Zhang , Jingrong Wu , Zhi Gao , Shilin Yan , Zhenxin Diao , Kunpeng Gao , Xuanyan Chen , Yuwei Wu , Yunde Jia , Qing Li

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Computation and Language · Computer Science 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences…

Computation and Language · Computer Science 2025-10-29 Sahar Abdelnabi , Ahmed Salem

Large language models (LLMs) have achieved strong performance on medical exam-style tasks, motivating growing interest in their deployment in real-world clinical settings. However, clinical decision-making is inherently safety-critical,…

Computation and Language · Computer Science 2026-04-13 Xiaohan Ren , Chenxiao Fan , Wenyin Ma , Hongliang He , Chongming Gao , Xiaoyan Zhao , Fuli Feng

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Artificial Intelligence · Computer Science 2026-05-29 Yang Ouyang , Shuhang Lin , Jung-Eun Kim

As agentic network management gains popularity, there is a critical need for evaluation frameworks that transcend static, one-shot testing. To address this, we introduce NetAgentBench, a dynamic benchmark that evaluates agent interactions…

Networking and Internet Architecture · Computer Science 2026-04-14 Ahmed Twabi , Yepeng Ding , Tohru Kondo