English
Related papers

Related papers: When Models Examine Themselves: Vocabulary-Activat…

200 papers

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

Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary is due to LLM's bias in evaluating their own output. In this…

Computation and Language · Computer Science 2024-06-19 Wenda Xu , Guanglei Zhu , Xuandong Zhao , Liangming Pan , Lei Li , William Yang Wang

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…

Artificial Intelligence · Computer Science 2025-12-17 Ge Yan , Chung-En Sun , Tsui-Wei , Weng

I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deployed language models. Our main benchmark uses Qwen 3.5 0.8B on four impossible-constraint…

Computation and Language · Computer Science 2026-05-21 Rana Muhammad Usman

Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and…

Machine Learning · Computer Science 2026-04-02 Sohan Venkatesh , Ashish Mahendran Kurapath

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

Computation and Language · Computer Science 2025-03-06 Shimao Zhang , Xiao Liu , Xin Zhang , Junxiao Liu , Zheheng Luo , Shujian Huang , Yeyun Gong

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

Computation and Language · Computer Science 2025-12-12 Weixiang Zhao , Xingyu Sui , Yulin Hu , Jiahe Guo , Haixiao Liu , Biye Li , Yanyan Zhao , Bing Qin , Ting Liu

Recent advances in automated theorem proving use Large Language Models (LLMs) to translate informal mathematical statements into formal proofs. However, informal cues are often ambiguous or lack strict logical structure, making it hard for…

Machine Learning · Computer Science 2025-10-14 Shashank Kirtania , Arun Iyer

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

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…

Computation and Language · Computer Science 2026-04-28 Shi Feng , Hanlin Zhang , Fan Nie , Sham Kakade , Yiling Chen

The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…

Artificial Intelligence · Computer Science 2026-01-09 Yaxuan Wang , Zhongteng Cai , Yujia Bao , Xueru Zhang , Yang Liu

Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article…

Machine Learning · Computer Science 2026-02-03 Vikram Krishnamurthy

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

Computation and Language · Computer Science 2026-03-24 Yuran Li , Di Wu , Benoit Boulet

While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating uncertainty. In this work, we identify what linguistic…

Computation and Language · Computer Science 2026-04-08 Shintaro Ozaki , Wataru Hashimoto , Hidetaka Kamigaito , Katsuhiko Hayashi , Taro Watanabe

Prior interpretability research studying narrow distributions has preliminarily identified self-repair, a phenomena where if components in large language models are ablated, later components will change their behavior to compensate. Our…

Machine Learning · Computer Science 2025-04-15 Cody Rushing , Neel Nanda

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

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores…

Computation and Language · Computer Science 2025-08-26 Rumi Allbert , James K. Wiles , Vlad Grankovsky