English
Related papers

Related papers: LLM Interpretability with Identifiable Temporal-In…

200 papers

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex dynamics that cannot be captured by simple functional mappings. Traditional approaches…

Machine Learning · Computer Science 2026-02-23 Preetom Biswas , Giulia Pedrielli , K. Selçuk Candan

While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we…

Computation and Language · Computer Science 2025-05-22 Zihao Jiang , Ben Liu , Miao Peng , Wenjie Xu , Yao Xiao , Zhenyan Shan , Min Peng

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…

Machine Learning · Computer Science 2024-12-03 Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Alasdair Newson , Matthieu Cord

Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visual/geometrical and textual representations of spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Raphi Kang , Hongqiao Chen , Georgia Gkioxari , Pietro Perona

Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanisms in exploiting this knowledge remains a key research area.…

Computation and Language · Computer Science 2024-08-07 Marco Bronzini , Carlo Nicolini , Bruno Lepri , Jacopo Staiano , Andrea Passerini

Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its…

Computation and Language · Computer Science 2026-05-04 Michael A. Lepori , Tal Linzen , Ann Yuan , Katja Filippova

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part…

Machine Learning · Computer Science 2025-09-29 Guan Zhe Hong , Bhavya Vasudeva , Vatsal Sharan , Cyrus Rashtchian , Prabhakar Raghavan , Rina Panigrahy

In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is the primary inference problem for many applications of topic…

Machine Learning · Computer Science 2025-06-10 Adam Breuer

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…

Reasoning about real-life events is a unifying challenge in AI and NLP that has profound utility in a variety of domains, while fallacy in high-stake applications could be catastrophic. Able to work with diverse text in these domains, large…

Computation and Language · Computer Science 2024-08-30 Li Zhang

Interpretability is a key challenge in fostering trust for Large Language Models (LLMs), which stems from the complexity of extracting reasoning from model's parameters. We present the Frame Representation Hypothesis, a theoretically robust…

Computation and Language · Computer Science 2025-11-25 Pedro H. V. Valois , Lincon S. Souza , Erica K. Shimomoto , Kazuhiro Fukui

Large Language Models (LLMs) demonstrate impressive capabilities but lack robust temporal intelligence, struggling to integrate reasoning about the past with predictions and plausible generations of the future. Meanwhile, existing methods…

Computation and Language · Computer Science 2025-06-04 Zijia Liu , Peixuan Han , Haofei Yu , Haoru Li , Jiaxuan You

Large Language Models (LLMs) have shown impressive performance across a wide range of tasks. However, the size of LLMs is steadily increasing, hindering their application on computationally constrained environments. On the other hand,…

Machine Learning · Computer Science 2024-12-23 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

Causal representation learning (CRL) seeks to recover latent variables with identifiability guarantees, typically up to permutation and component-wise reparameterization under appropriate assumptions. However, identifiability does not imply…

Machine Learning · Computer Science 2026-05-08 Shicheng Fan , Nour Elhendawy , Jianle Sun , Ke Fang , Kun Zhang , Yihang Wang , Lu Cheng

Why does a phenomenon occur? Addressing this question is central to most scientific inquiries and often relies on simulations of scientific models. As models become more intricate, deciphering the causes behind phenomena in high-dimensional…

Machine Learning · Statistics 2024-06-04 Armin Kekić , Bernhard Schölkopf , Michel Besserve

Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Hyeonjeong Ha , Jinjin Ge , Bo Feng , Kaixin Ma , Gargi Chakraborty

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Computation and Language · Computer Science 2025-07-10 Shun Wang , Tyler Loakman , Youbo Lei , Yi Liu , Bohao Yang , Yuting Zhao , Dong Yang , Chenghua Lin