English
Related papers

Related papers: Towards Understanding Steering Strength

200 papers

Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a…

Computation and Language · Computer Science 2026-04-14 Ziwen Xu , Kewei Xu , Haoming Xu , Haiwen Hong , Longtao Huang , Hui Xue , Ningyu Zhang , Yongliang Shen , Guozhou Zheng , Huajun Chen , Shumin Deng

Large Language Models (LLMs) are increasingly consulted for high-stakes life advice, yet they lack standard safeguards against providing confident but misguided responses. This creates risks of sycophancy and over-confidence. This paper…

Artificial Intelligence · Computer Science 2025-07-30 Joshua Adrian Cahyono , Saran Subramanian

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Several machine learning methods aim to learn or reason about complex physical systems. A common first-step towards reasoning is to infer system parameters from observations of its behavior. In this paper, we investigate the performance of…

Computation and Language · Computer Science 2024-02-07 Sean Memery , Mirella Lapata , Kartic Subr

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and decision commitment evolve along a reasoning trajectory, and…

Machine Learning · Computer Science 2026-02-02 Marthe Ballon , Brecht Verbeken , Vincent Ginis , Andres Algaba

Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly valuable tools to characterize and control LLMs' behavior,…

Computation and Language · Computer Science 2026-01-19 Michel Frising , Daniel Balcells

Traffic prediction, an essential component for intelligent transportation systems, endeavours to use historical data to foresee future traffic features at specific locations. Although existing traffic prediction models often emphasize…

Machine Learning · Computer Science 2024-07-09 Chenxi Liu , Sun Yang , Qianxiong Xu , Zhishuai Li , Cheng Long , Ziyue Li , Rui Zhao

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

Computation and Language · Computer Science 2025-07-17 Yanjian Zhang , Guillaume Wisniewski , Nadi Tomeh , Thierry Charnois

Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Therefore, it is of great importance to evaluate their emerging abilities. In this study, we show that LLMs…

Computation and Language · Computer Science 2023-10-10 Thilo Hagendorff , Sarah Fabi , Michal Kosinski

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…

Computation and Language · Computer Science 2025-10-30 Chunyuan Deng , Ruidi Chang , Hanjie Chen

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Computation and Language · Computer Science 2026-05-07 Mikhail L. Arbuzov , Sisong Bei , Ziwei Dong , Dmitri Kalaev , Alexey A. Shvets

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal…

Computation and Language · Computer Science 2026-04-16 Simon Ostermann , Daniil Gurgurov , Tanja Baeumel , Michael A. Hedderich , Sebastian Lapuschkin , Wojciech Samek , Vera Schmitt

We investigate whether large language models (LLMs) can predict whether they will succeed on a given task and whether their predictions improve as they progress through multi-step tasks. We also investigate whether LLMs can learn from…

Computation and Language · Computer Science 2026-01-01 Casey O. Barkan , Sid Black , Oliver Sourbut

Large language models (LLMs) with billions of parameters exhibit in-context learning abilities, enabling few-shot learning on tasks that the model was not specifically trained for. Traditional models achieve breakthrough performance on…

Artificial Intelligence · Computer Science 2025-11-04 Aske Plaat , Annie Wong , Suzan Verberne , Joost Broekens , Niki van Stein , Thomas Back

Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensive tasks through the generation of supplementary planning tokens. This development raises a…

Computation and Language · Computer Science 2026-04-29 Pratham Singla , Shivank Garg , Ayush Singh , Ishan Garg , Ketan Suhaas Saichandran

Phase transitions have been proposed as the origin of emergent abilities in large language models (LLMs), where new capabilities appear abruptly once models surpass critical thresholds of scale. Prior work, such as that of Wei et al.,…

Computation and Language · Computer Science 2025-11-18 Noah Hong , Tao Hong

The widespread public deployment of large language models (LLMs) in recent months has prompted a wave of new attention and engagement from advocates, policymakers, and scholars from many fields. This attention is a timely response to the…

Computation and Language · Computer Science 2023-04-04 Samuel R. Bowman

Steering vectors (SVs) have been proposed as an effective approach to adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and…

Machine Learning · Computer Science 2025-05-06 Daniel Tan , David Chanin , Aengus Lynch , Dimitrios Kanoulas , Brooks Paige , Adria Garriga-Alonso , Robert Kirk

Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to high latency from excessive token generation, or unstable…

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

Computation and Language · Computer Science 2026-04-17 Shiwan Zhao , Zhihu Wang , Xuyang Zhao , Jiaming Zhou , Caiyue Xu , Chenfei Liu , Liting Zhang , Yuhang Jia , Yanzhe Zhang , Hualong Yu , Zichen Xu , Qicheng Li , Yong Qin