English
Related papers

Related papers: CircuitProbe: Predicting Reasoning Circuits in Tra…

200 papers

Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demonstrate that state-of-the-art models (Qwen2.5-Math-7B)…

Machine Learning · Computer Science 2026-03-05 Subramanyam Sahoo , Aman Chadha , Vinija Jain , Divya Chaudhary

Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. This calls for empirical and theoretical explorations of…

Artificial Intelligence · Computer Science 2025-04-02 Federico Adolfi , Martina G. Vilas , Todd Wareham

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Computation and Language · Computer Science 2025-10-17 Stephen Chung , Wenyu Du , Jie Fu

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what…

Artificial Intelligence · Computer Science 2026-01-09 Danchun Chen , Qiyao Yan , Liangming Pan

Large Language Models often achieve strong performance by generating long intermediate chain-of-thought reasoning. However, it remains unclear when a model's final answer is actually determined during generation. If the answer is already…

Computation and Language · Computer Science 2026-04-27 Ayan Datta , Zhixue Zhao , Bhuvanesh Verma , Radhika Mamidi , Mounika Marreddy , Alexander Mehler

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

Software Engineering · Computer Science 2026-05-06 Lishui Fan , Yu Zhang , Mouxiang Chen , Zhongxin Liu

Explaining why a language model produces a particular output requires local, input-level explanations. Existing methods uncover global capability circuits (e.g., indirect object identification), but not why the model answers a specific…

Artificial Intelligence · Computer Science 2025-09-30 Tung-Yu Wu , Fazl Barez

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem…

Machine Learning · Computer Science 2025-06-23 Guan Zhe Hong , Nishanth Dikkala , Enming Luo , Cyrus Rashtchian , Xin Wang , Rina Panigrahy

Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited…

Artificial Intelligence · Computer Science 2025-12-12 Muhammad Umair Haider , Hammad Rizwan , Hassan Sajjad , A. B. Siddique

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

Reasoning models (e.g., DeepSeek-R1) generate long chains of thought to solve harder problems, but they often loop, repeating the same text at low temperatures or with greedy decoding. We study why this happens and what role temperature…

This paper concerns the problem of checking if two shallow (i.e., constant-depth) quantum circuits perform equivalent computations. Equivalence checking is a fundamental correctness question -- needed, e.g., for ensuring that…

Quantum Physics · Physics 2025-04-03 Nengkun Yu , Xuan Du Trinh , Thomas Reps

Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settings. In this work, we ask whether the long CoTs can be…

Computation and Language · Computer Science 2025-10-08 Yik Siu Chan , Zheng-Xin Yong , Stephen H. Bach

While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called…

Computation and Language · Computer Science 2024-10-08 Michael Lan , Philip Torr , Fazl Barez

Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and…

Computation and Language · Computer Science 2025-06-13 Jaechul Roh , Varun Gandhi , Shivani Anilkumar , Arin Garg

A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be composed to perform more complex tasks. Recent advances in…

Machine Learning · Computer Science 2025-06-24 Philipp Mondorf , Sondre Wold , Barbara Plank

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code…

Machine Learning · Computer Science 2026-05-19 Zhanyue Qin , Jia Feng , Yibo Lyu , Yun Peng , Dianbo Sui , Cuiyun Gao , Qing Liao

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

Artificial Intelligence · Computer Science 2025-10-08 Renee Ge , Qianli Liao , Tomaso Poggio

Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining representations within hidden states. This…

Computation and Language · Computer Science 2026-03-12 Markus Frey , Behzad Shomali , Ali Hamza Bashir , David Berghaus , Joachim Koehler , Mehdi Ali