English
Related papers

Related papers: Mitigating Content Effects on Reasoning in Languag…

200 papers

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…

Computation and Language · Computer Science 2025-11-21 Sangmook Lee , Dohyung Kim , Hyukhun Koh , Nakyeong Yang , Kyomin Jung

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical…

Computation and Language · Computer Science 2026-01-28 Fangan Dong , Zuming Yan , Xuri Ge , Zhiwei Xu , Mengqi Zhang , Xuanang Chen , Ben He , Xin Xin , Zhumin Chen , Ying Zhou

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected attention heads,…

Computation and Language · Computer Science 2026-02-05 Zijian Feng , Tianjiao Li , Zixiao Zhu , Hanzhang Zhou , Junlang Qian , Li Zhang , Jia Jim Deryl Chua , Lee Onn Mak , Gee Wah Ng , Kezhi Mao

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…

Computation and Language · Computer Science 2023-12-08 Ole Jorgensen , Dylan Cope , Nandi Schoots , Murray Shanahan

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Computation and Language · Computer Science 2025-10-14 Jialu Du , Guiyang Hou , Yihui Fu , Chen Wu , Wenqi Zhang , Yongliang Shen , Weiming Lu

Interpretability methods for large language models (LLMs) typically derive directions from textual supervision, which can lack external grounding. We propose using human brain activity not as a training signal but as a coordinate system for…

Machine Learning · Computer Science 2025-12-24 Sandro Andric

Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…

Computation and Language · Computer Science 2025-06-25 C. Nicolò De Sabbata , Theodore R. Sumers , Badr AlKhamissi , Antoine Bosselut , Thomas L. Griffiths

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Artificial Intelligence · Computer Science 2026-05-11 Aayush Mishra , Daniel Khashabi , Anqi Liu

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…

Computation and Language · Computer Science 2026-01-13 Nikhil Anand , Shwetha Somasundaram , Anirudh Phukan , Apoorv Saxena , Koyel Mukherjee

The limited reasoning capabilities of small language models (SLMs) cast doubt on their suitability for tasks demanding deep, multi-step logical deduction. This paper introduces a framework called Small Reasons, Large Hints (SMART), which…

Computation and Language · Computer Science 2025-06-03 Yujin Kim , Euiin Yi , Minu Kim , Se-Young Yun , Taehyeon Kim

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Computation and Language · Computer Science 2026-05-29 Yingdong Shi , Ruiming Zhang , Changming Li , Zhiyu Yang , Kaixing Zhang , Jingyi Yu , Kan Ren

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Computation and Language · Computer Science 2025-10-27 Yiju Guo , Wenkai Yang , Zexu Sun , Ning Ding , Zhiyuan Liu , Yankai Lin

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Machine Learning · Computer Science 2025-07-28 Bertram Højer , Oliver Jarvis , Stefan Heinrich

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

Computational Engineering, Finance, and Science · Computer Science 2025-09-26 Hong Su

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activations more interpretable by exposing latent features that often…

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is…

Computation and Language · Computer Science 2026-04-21 Leonardo Bertolazzi , Sandro Pezzelle , Raffaella Bernardi

As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints in mind, Knowledge Editing (KE) approaches propose to alter…

Artificial Intelligence · Computer Science 2025-07-30 Marco Scialanga , Thibault Laugel , Vincent Grari , Marcin Detyniecki