English
Related papers

Related papers: Decomposing and Steering Functional Metacognition …

200 papers

To enable Large Language Models (LLMs) to function as conscious agents with generalizable reasoning capabilities, it is crucial that they possess the reasoning ability to comprehend situational changes (transitions) in distribution…

Computation and Language · Computer Science 2025-05-22 Weiqi Wang , Yangqiu Song

Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this…

Computation and Language · Computer Science 2026-01-14 Zhenghao He , Guangzhi Xiong , Bohan Liu , Sanchit Sinha , Aidong Zhang

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Machine Learning · Computer Science 2025-10-23 Constantin Venhoff , Iván Arcuschin , Philip Torr , Arthur Conmy , Neel Nanda

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT) practices. However, whether fundamental reasoning…

Computation and Language · Computer Science 2026-05-28 Xingwei Tan , Marco Valentino , Mahmud Elahi Akhter , Yuxiang Zhou , Maria Liakata , Nikolaos Aletras

The possibility of LLM self-awareness and even sentience is gaining increasing public attention and has major safety and policy implications, but the science of measuring them is still in a nascent state. Here we introduce a novel…

Machine Learning · Computer Science 2026-03-26 Christopher Ackerman

Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that require specialized processing or up-to-date data. While…

Computation and Language · Computer Science 2025-08-22 Wenjun Li , Dexun Li , Kuicai Dong , Cong Zhang , Hao Zhang , Weiwen Liu , Yasheng Wang , Ruiming Tang , Yong Liu

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

Machine Learning · Computer Science 2024-11-08 Anthony Costarelli , Mat Allen , Severin Field

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

Computation and Language · Computer Science 2024-04-17 Haiyan Zhao , Fan Yang , Bo Shen , Himabindu Lakkaraju , Mengnan Du

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

Machine Learning · Computer Science 2023-11-02 Fabien Roger , Ryan Greenblatt

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Artificial Intelligence · Computer Science 2026-05-28 Phuong Minh Nguyen , Tien Huu Dang , Naoya Inoue

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

Computation and Language · Computer Science 2024-06-04 Yiming Wang , Zhuosheng Zhang , Pei Zhang , Baosong Yang , Rui Wang

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstrates that confidence signals can be extracted from language model outputs, yet a fundamental…

Machine Learning · Computer Science 2026-05-20 Dharshan Kumaran , Nathaniel Daw , Simon Osindero , Petar Veličković , Viorica Patraucean

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Computation and Language · Computer Science 2025-02-25 Moritz Miller , Kumar Shridhar

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…

Computation and Language · Computer Science 2025-05-27 Junnan Liu , Hongwei Liu , Linchen Xiao , Shudong Liu , Taolin Zhang , Zihan Ma , Songyang Zhang , Kai Chen

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive…

Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally inherent stereotypes, cloud moral judgments, or amplify positive evaluations of majority groups. Previous explanations mainly attributed bias in LLMs…

Artificial Intelligence · Computer Science 2024-08-13 Florian Scholten , Tobias R. Rebholz , Mandy Hütter

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial…

Computation and Language · Computer Science 2026-03-30 Jiyuan An , Liner Yang , Mengyan Wang , Luming Lu , Weihua An , Erhong Yang

Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon known as content effect. This bias persists even when models…

Computation and Language · Computer Science 2026-02-03 Gabriele Maraia , Marco Valentino , Fabio Massimo Zanzotto , Leonardo Ranaldi