English
Related papers

Related papers: Data-driven Circuit Discovery for Interpretability…

200 papers

Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV-cache compatibility, prior work commonly adopts block-based…

Computation and Language · Computer Science 2026-01-21 Yingte Shu , Yuchuan Tian , Chao Xu , Yunhe Wang , Hanting Chen

With the rapid advancement of neural language models, the deployment of over-parameterized models has surged, increasing the need for interpretable explanations comprehensible to human inspectors. Existing post-hoc interpretability methods,…

Artificial Intelligence · Computer Science 2024-11-08 Zijian Zhang , Vinay Setty , Yumeng Wang , Avishek Anand

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and…

Artificial Intelligence · Computer Science 2026-02-03 Wei Yang , Hong Xie , Tao Tan , Xin Li , Defu Lian , Enhong Chen

Metaphor detection, a critical task in natural language processing, involves identifying whether a particular word in a sentence is used metaphorically. Traditional approaches often rely on supervised learning models that implicitly encode…

Computation and Language · Computer Science 2024-12-30 Yujie Lin , Jingyao Liu , Yan Gao , Ante Wang , Jinsong Su

Large Language Models (LLMs) have experienced a rapid rise in AI, changing a wide range of applications with their advanced capabilities. As these models become increasingly integral to decision-making, the need for thorough…

Machine Learning · Computer Science 2024-01-09 Jatin Nainani

Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But…

Machine Learning · Computer Science 2024-06-28 Achille Nazaret , Justin Hong , Elham Azizi , David Blei

Large language models (LLMs) have demonstrated impressive reasoning capabilities, but scaling their performance often relies on massive reasoning datasets that are computationally expensive to train on. Existing data selection methods aim…

Artificial Intelligence · Computer Science 2025-10-24 Shaobo Wang , Yongliang Miao , Yuancheng Liu , Qianli Ma , Ning Liao , Linfeng Zhang

While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipulable model of the world. As a consequence, current LMs also…

Computation and Language · Computer Science 2024-06-28 Afra Feyza Akyürek , Ekin Akyürek , Leshem Choshen , Derry Wijaya , Jacob Andreas

Transforming a dynamic hypothesis into a causal loop diagram (CLD) is crucial for System Dynamics Modelling. Extracting key variables and causal relationships from text to build a CLD is often challenging and time-consuming for novice…

Machine Learning · Computer Science 2025-03-31 Ning-Yuan Georgia Liu , David R. Keith

To date, most discoveries of network subcomponents that implement human-interpretable computations in deep vision models have involved close study of single units and large amounts of human labor. We explore scalable methods for extracting…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Achyuta Rajaram , Neil Chowdhury , Antonio Torralba , Jacob Andreas , Sarah Schwettmann

Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…

Computation and Language · Computer Science 2025-07-17 Huaizhi Ge , Frank Rudzicz , Zining Zhu

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

The ability to understand causality from data is one of the major milestones of human-level intelligence. Causal Discovery (CD) algorithms can identify the cause-effect relationships among the variables of a system from related…

Artificial Intelligence · Computer Science 2024-03-14 Uzma Hasan , Emam Hossain , Md Osman Gani

Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to multi-system data backends surfaces a harder problem: the search space is heterogeneous,…

Artificial Intelligence · Computer Science 2026-05-27 Shanshan Ye , Duo Lu

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jingcheng Yang , Tianhu Xiong , Shengyi Qian , Klara Nahrstedt , Mingyuan Wu

Learning causal structure from observational data is a fundamental challenge in machine learning. However, the majority of commonly used differentiable causal discovery methods are non-identifiable, turning this problem into a continuous…

Machine Learning · Computer Science 2022-09-30 Yu Wang , An Zhang , Xiang Wang , Yancheng Yuan , Xiangnan He , Tat-Seng Chua

Identifying suitable datasets for a research question remains challenging because existing dataset search engines rely heavily on metadata quality and keyword overlap, which often fail to capture the semantic intent of scientific…

Digital Libraries · Computer Science 2026-01-09 Zhiyin Tan , Changxu Duan

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Computation and Language · Computer Science 2025-12-03 Kecheng Chen , Ziru Liu , Xijia Tao , Hui Liu , Xinyu Fu , Suiyun Zhang , Dandan Tu , Lingpeng Kong , Rui Liu , Haoliang Li

In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the…

Computation and Language · Computer Science 2025-02-21 Hakaze Cho , Mariko Kato , Yoshihiro Sakai , Naoya Inoue

Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data often arrive in batches, are subject to sampling bias, and expert knowledge is scarce. Language…

Machine Learning · Computer Science 2026-05-12 Prakhar Verma , David Arbour , Sunav Choudhary , Harshita Chopra , Arno Solin , Atanu R. Sinha