English
Related papers

Related papers: From Sequence to Structure: Uncovering Substructur…

200 papers

Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical…

Machine Learning · Computer Science 2026-04-09 Philipp Hellwig , Willem Zuidema , Claire E. Stevenson , Martha Lewis

Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understood. We investigate how transformers perform \textit{transitive inference}, a classic…

Machine Learning · Computer Science 2026-05-12 Jesse Geerts , Andrew Liu , Stephanie Chan , Claudia Clopath , Kimberly Stachenfeld

As large language models (LLMs) become more capable, there is an urgent need for interpretable and transparent tools. Current methods are difficult to implement, and accessible tools to analyze model internals are lacking. To bridge this…

Machine Learning · Computer Science 2023-11-30 Albert Garde , Esben Kran , Fazl Barez

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Machine Learning · Computer Science 2025-10-21 Jing Liu

Pretrained Large Language Models (LLMs) have demonstrated various reasoning capabilities through language-based prompts alone, particularly in unstructured task settings (tasks purely based on language semantics). However, LLMs often…

Computation and Language · Computer Science 2024-08-30 Palaash Agrawal , Shavak Vasania , Cheston Tan

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…

Computation and Language · Computer Science 2024-07-16 Parag Jain , Mirella Lapata

Attention mechanisms are critical to the success of large language models (LLMs), driving significant advancements in multiple fields. However, for graph-structured data, which requires emphasis on topological connections, they fall short…

Artificial Intelligence · Computer Science 2025-05-06 Zhong Guan , Likang Wu , Hongke Zhao , Ming He , Jianpin Fan

Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization abilities of…

Machine Learning · Computer Science 2026-02-10 Xinting Huang , Aleksandra Bakalova , Satwik Bhattamishra , William Merrill , Michael Hahn

Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In…

Artificial Intelligence · Computer Science 2024-07-12 Randall Balestriero , Romain Cosentino , Sarath Shekkizhar

The emergence of large-scale pre-trained language models has revolutionized various AI research domains. Transformers-based Large Language Models (LLMs) have gradually replaced CNNs and RNNs to unify fields of computer vision and natural…

Computation and Language · Computer Science 2024-02-07 Ruosong Ye , Caiqi Zhang , Runhui Wang , Shuyuan Xu , Yongfeng Zhang

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

Computation and Language · Computer Science 2026-05-26 Nura Aljaafari , Marco Valentino , André Freitas

Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in…

Biomolecules · Quantitative Biology 2026-05-19 Zhiyuan Yan , Chen Liu , Boxuan Zhao , Kaiqing Lin , Jixiang Zhao , Yimi Wang , Liuzhenghao Lv , Hao Li , Shanzhuo Zhang , Li Yuan , Fanyang Mo

The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to…

Computation and Language · Computer Science 2023-10-10 Ziwei Chai , Tianjie Zhang , Liang Wu , Kaiqiao Han , Xiaohai Hu , Xuanwen Huang , Yang Yang

Large Language Models (LLMs) have demonstrated the ability to solve complex tasks through In-Context Learning (ICL), where models learn from a few input-output pairs without explicit fine-tuning. In this paper, we explore the capacity of…

Machine Learning · Computer Science 2024-11-26 Paimon Goulart , Evangelos E. Papalexakis

Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity…

Machine Learning · Computer Science 2026-02-11 Andres Saurez , Yousung Lee , Dongsoo Har

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Computation and Language · Computer Science 2023-11-30 Haiyan Zhao , Hanjie Chen , Fan Yang , Ninghao Liu , Huiqi Deng , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Mengnan Du

Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e.g., their ability…

Computation and Language · Computer Science 2025-05-05 Core Francisco Park , Andrew Lee , Ekdeep Singh Lubana , Yongyi Yang , Maya Okawa , Kento Nishi , Martin Wattenberg , Hidenori Tanaka

While Large Language Models (LLMs) are increasingly deployed for table-related tasks, the internal mechanisms enabling them to process linearized two-dimensional structured tables remain opaque. In this work, we investigate the process of…

Computation and Language · Computer Science 2026-02-10 Xuanliang Zhang , Dingzirui Wang , Keyan Xu , Qingfu Zhu , Wanxiang Che

Transformers, as the fundamental deep learning architecture, have demonstrated great capability in reasoning. This paper studies the generalizable first-order logical reasoning ability of transformers with their parameterized knowledge and…

Computation and Language · Computer Science 2025-07-11 Tianshi Zheng , Jiazheng Wang , Zihao Wang , Jiaxin Bai , Hang Yin , Zheye Deng , Yangqiu Song , Jianxin Li

Recent works on form understanding mostly employ multimodal transformers or large-scale pre-trained language models. These models need ample data for pre-training. In contrast, humans can usually identify key-value pairings from a form only…

Computation and Language · Computer Science 2023-05-09 Bhanu Prakash Voutharoja , Lizhen Qu , Fatemeh Shiri