Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies on reasoning in language models have sparked a debate on whether they can learn systematic inferential principles or merely exploit superficial patterns in the training data. |
| Approach: | They propose a method for circuit discovery aimed at interpreting syllogistic inference . they uncover a circuit involving middle-term suppression that elucidates how LMs transfer information to derive valid conclusions from premises. |
| Outcome: | The proposed method elucidates how LMs transfer information to derive valid conclusions from premises. |
Similar Papers
A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences (2024.emnlp-main)
Copied to clipboard
| Challenge: | syllogistic reasoning is a deductive reasoning skill that is crucial in everyday problem-solving and decision-making experiences. |
| Approach: | They propose to study the reasoning abilities of Large Language Models (LLMs) they propose to use supervised fine-tuning and chain-of-thought reasoning to investigate their results. |
| Outcome: | The proposed models exhibit reasoning biases, avoid answering that no conclusion follows, align with human difficulties, and struggle with multi-step reasoning. |
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models (2023.emnlp-main)
Copied to clipboard
Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
| Challenge: | Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. |
| Approach: | They propose a mechanistic interpretation of language models for multi-step reasoning tasks by introducing a new probing approach that recovers the reasoning tree from the model’s attention patterns. |
| Outcome: | The proposed model implicitly embeds a reasoning tree resembling the correct reasoning process within it, and detects the information from the model’s attention patterns for most examples. |
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models implicitly embed reasoning trees, but their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. |
| Approach: | They propose to use circuit analysis and self-influence functions to map the reasoning process of large models. |
| Outcome: | The proposed model is able to map human-interpretable reasoning paths and a model's underlying circuits reveal human-mediated reasoning processes. |
A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Psychologists have documented several ways in which humans’ inferences deviate from the rules of logic. |
| Approach: | They focus on syllogisms, which are inferences from two simple premises, and show that larger models are more logical than smaller ones. |
| Outcome: | The results show that language models often mimic human biases, but overcome them in some cases. |
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)
Copied to clipboard
Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan
| Challenge: | Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors. |
| Approach: | They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors. |
| Outcome: | This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies . |
Can Activation Steering Generalize Across Languages? A Study on Syllogistic Reasoning in Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Prior work has focused on activation steering for Large Language Models (LLMs) this technique can be used to improve reasoning accuracy and transferability across languages. |
| Approach: | They propose to use activation steering to steer models towards a cross-lingual reasoning space. |
| Outcome: | The proposed techniques generalise well to multilingual datasets while minimizing language modelling performance. |
Complex Reasoning in Natural Language (2023.acl-tutorials)
Copied to clipboard
| Challenge: | Recent research shows that pretrained language models are often brittle for complex reasoning tasks. |
| Approach: | They propose to use pre-trained language models to teach machines to reason over texts . they will review recent promising approaches to tackling complex reasoning tasks . |
| Outcome: | This tutorial reviews promising approaches to complex reasoning tasks . it reviews the methods that can be used to augment models with robustness . |
A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on how large language models process and store information related to arithmetic tasks have shown their behavior inconsistent and context-dependent. |
| Approach: | They propose to mechanize the processing of arithmetic queries by a causal mediation framework. |
| Outcome: | The proposed model improves the performance of arithmetic queries with a set of MLP modules. |
Exploring Reasoning Biases in Large Language Models Through Syllogism: Insights from the NeuBAROCO Dataset (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models of large language reasoning exhibit reasoning biases similar to humans, a study shows . syllogistic reasoning is one of the basic forms of deductive reasoning . |
| Approach: | They propose to use a syllogism dataset to evaluate models' reasoning abilities . they propose to ask LLMs to translate slogismatic slurs into abstract logical expressions . |
| Outcome: | The proposed method shows that models exhibit reasoning biases similar to humans, and that there is room for improvement in reasoning problems where premises and hypotheses are neither entailment nor contradiction. |
Uncovering Sentiment Analysis Circuit in Large Language Model (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that sentiment is encoded linearly in LLM representations, but their ability to utilize this information remains fragile to prompt variations. |
| Approach: | They propose a simple inference-time intervention method that amplifies circuit features to compensate for insufficient activation. |
| Outcome: | The proposed method improves on a sentiment analysis circuit with sparse autoencoders and circuit-level analysis. |