English
Related papers

Related papers: Superscopes: Amplifying Internal Feature Represent…

200 papers

While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different…

Computation and Language · Computer Science 2023-02-01 Daking Rai , Yilun Zhou , Bailin Wang , Ziyu Yao

Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their…

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

Understanding the internal mechanisms of large audio-language models (LALMs) is crucial for interpreting their behavior and improving performance. This work presents the first in-depth analysis of how LALMs internally perceive and recognize…

Computation and Language · Computer Science 2025-08-26 Chih-Kai Yang , Neo Ho , Yi-Jyun Lee , Hung-yi Lee

The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in…

Artificial Intelligence · Computer Science 2023-05-22 Liting Chen , Lu Wang , Hang Dong , Yali Du , Jie Yan , Fangkai Yang , Shuang Li , Pu Zhao , Si Qin , Saravan Rajmohan , Qingwei Lin , Dongmei Zhang

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer layers (space), and varying model sizes (scale). Using…

Computation and Language · Computer Science 2025-05-27 Shashata Sawmya , Micah Adler , Nir Shavit

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Kaiqing Lin , Yuzhen Lin , Weixiang Li , Taiping Yao , Bin Li

Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This paper addresses the problem of learning object structures in an…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Yuting Zhang , Yijie Guo , Yixin Jin , Yijun Luo , Zhiyuan He , Honglak Lee

Large language models (LLMs) have demonstrated broad utility across molecular domains, spanning drug discovery and materials design. Analyzing LLMs' latent representations is crucial for elucidating their underlying mechanisms, improving…

Machine Learning · Computer Science 2026-02-03 Zhuoran Li , Xu Sun , Wanyu Lin , Jiannong Cao

An emerging family of language models (LMs), capable of processing both text and images within a single visual view, has the promise to unlock complex tasks such as chart understanding and UI navigation. We refer to these models as…

Computation and Language · Computer Science 2024-02-27 Tianyu Gao , Zirui Wang , Adithya Bhaskar , Danqi Chen

We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can…

We draw inspiration from microsaccades, tiny involuntary eye movements that reveal hidden dynamics of human perception, to propose an analogous probing method for large language models (LLMs). Just as microsaccades expose subtle but…

Machine Learning · Computer Science 2025-10-03 Rui Melo , Rui Abreu , Corina S. Pasareanu

Large Language Models (LLMs) have revolutionized various domains with extensive knowledge and creative capabilities. However, a critical issue with LLMs is their tendency to produce outputs that diverge from factual reality. This phenomenon…

Computation and Language · Computer Science 2024-07-19 Jinwen He , Yujia Gong , Kai Chen , Zijin Lin , Chengan Wei , Yue Zhao

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical computations. However, even for the simplest…

Computation and Language · Computer Science 2024-09-04 Wei Zhang , Chaoqun Wan , Yonggang Zhang , Yiu-ming Cheung , Xinmei Tian , Xu Shen , Jieping Ye

Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic notations, with emerging extensions to incorporate multi-modal…

Machine Learning · Computer Science 2025-05-23 Ziqing Wang , Kexin Zhang , Zihan Zhao , Yibo Wen , Abhishek Pandey , Han Liu , Kaize Ding

Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue, based on lessons from human metacognition research, that this conclusion may be…

Artificial Intelligence · Computer Science 2026-05-27 Shashwat Singh , Tal Linzen , Shauli Ravfogel

In the deployment of large language models (LLMs), accurate confidence estimation is critical for assessing the credibility of model predictions. However, existing methods often fail to overcome the issue of overconfidence on incorrect…

Computation and Language · Computer Science 2024-02-20 Pei Wang , Yejie Wang , Muxi Diao , Keqing He , Guanting Dong , Weiran Xu

Language models (LMs) often generate incoherent outputs: they refer to events and entity states that are incompatible with the state of the world described in their inputs. We introduce SituationSupervision, a family of approaches for…

Computation and Language · Computer Science 2022-12-21 Belinda Z. Li , Maxwell Nye , Jacob Andreas

Recently, large language models (LLMs) have shown remarkable capabilities including understanding context, engaging in logical reasoning, and generating responses. However, this is achieved at the expense of stringent computational and…

Computation and Language · Computer Science 2024-05-30 Xindi Wang , Mahsa Salmani , Parsa Omidi , Xiangyu Ren , Mehdi Rezagholizadeh , Armaghan Eshaghi