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. |
Similar Papers
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism (2025.findings-emnlp)
Copied to clipboard
Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu
| Challenge: | Large language models struggle with complex reasoning tasks, such as mathematical problem-solving. |
| Approach: | They constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning. |
| Outcome: | The proposed algorithm improves on 7 multi-step reasoning datasets, while introducing only 132 trainable parameters. |
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. |
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. |
Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are essential for performing complex multi-step reasoning tasks, such as multi-hop reasoning tasks. |
| Approach: | They propose to use large language models to derive structured intermediate proof steps to improve their performance by using examples. |
| Outcome: | The proposed models can derive correct proof steps with in-context learning. |
Learning Multi-Step Reasoning by Solving Arithmetic Tasks (2023.acl-short)
Copied to clipboard
| Challenge: | Recent studies have demonstrated large LMs’ impressive performance in solving math problems, but such ability seems only to emerge from models with abundant parameters. |
| Approach: | They propose to continuously pre-train LMs with the capabilities of multi-step reasoning by continuously pretraining them on a synthetic dataset MsAT. |
| Outcome: | The proposed method improves LMs' multi-step reasoning abilities on four math word problem datasets. |
From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to solve complex logical reasoning problems are cumbersome for language models. |
| Approach: | They propose to use iterative methodology to construct a cognitive tree using language models . they propose to generate multiple responses by utilizing in-context examples . |
| Outcome: | The proposed model achieves a performance level comparable to that of GPT-3.5 . the proposed model contains fewer parameters than 5% of the model with 175B parameters . |
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for ensembling language models fail to address complex reasoning tasks. |
| Approach: | They propose a framework for process-level ensembling of large language models using Monte Carlo tree search. |
| Outcome: | The proposed framework outperforms both language model decoding and language model ensemble methods on five reasoning benchmarks. |
LM2: A Simple Society of Language Models Solves Complex Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that providing guidance via decomposing the original question into multiple subproblems elicits more robustness in LLM reasoning. |
| Approach: | They propose a language-based decomposition, solution and verification framework that modularizes the decomposer, solution, and verification into three different language models. |
| Outcome: | The proposed model outperforms existing methods on in- and out-domain reasoning problems, outperforming the best baselines by 8.1% on MATH, 7.71% on JEEBench, and 9.7% on MedQA problems. |
From Sentences to Proof Trees: Leveraging Language Models for Structured Reasoning (2026.eacl-srw)
Copied to clipboard
| Challenge: | Multi-hop reasoning requires a chain of facts to reflect the reasoning behind the answer. |
| Approach: | They propose an inference-guided prompting approach that performs well in natural language questions . they propose a neuro-symbolic approach to reasoning using large language models . |
| Outcome: | The proposed model outperforms all prompting strategies and fine-tunes LLMs trained specifically for proof generation. |
First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning (2024.emnlp-main)
Copied to clipboard
Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Keisuke Sakaguchi, Kentaro Inui
| Challenge: | Explicit multi-step reasoning is widely adopted to improve the performance of language models. |
| Approach: | They propose a systematic reasoning strategy that LMs use to solve multi-step reasoning tasks. |
| Outcome: | The proposed strategy improves the performance of language models by combining heuristics with rational strategies. |