Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals (2024.acl-long)
Copied to clipboard
| Challenge: | Existing interpretability research focused on analyzing a single mechanism . et al., 2023) focused on finding how models copy or recall factual knowledge . |
| Approach: | They propose a competition of mechanisms that focuses on the interplay of multiple mechanisms instead of individual mechanisms . they uncover how and where the competition of mechanism happens within LLMs using logit inspection and attention modification methods. |
| Outcome: | The proposed model is based on two interpretability methods, logit inspection and attention modification. |
Similar Papers
Knowledge Mechanisms in Large Language Models: A Survey and Perspective (2024.findings-emnlp)
Copied to clipboard
Mengru Wang, Yunzhi Yao, Ziwen Xu, Shuofei Qiao, Shumin Deng, Peng Wang, Xiang Chen, Jia-Chen Gu, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang
| Challenge: | Using large language models, we can understand knowledge mechanisms in LLMs for learning, storage, utilization, and evolution. |
| Approach: | They propose to analyze knowledge mechanisms in Large Language Models (LLMs) they examine utilization, evolution, and the potential dark knowledge (hypothesis) they hope to help understand knowledge in LLMs and provide insights for future research . |
| Outcome: | The proposed model can be used to analyze the evolution of parametric knowledge in LLMs. |
Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in language models have demonstrated their ability to process linguistic expressions with complex syntactic structures. |
| Approach: | They investigate whether language models employ shared neural mechanisms across different constructions by applying causal interpretability methods at a granular level. |
| Outcome: | The proposed model performance improves on acceptability judgment benchmarks. |
Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have not evaluated whether probing accuracy predicts syntactic outcomes. |
| Approach: | They evaluate 32 open-weight transformer models and find that probing fails to predict outcomes of targeted syntax evaluations across English linguistic phenomena. |
| Outcome: | The proposed model does not predict syntactic outcomes on English linguistic phenomena. |
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior research on linguistic mechanisms of large language models is limited by coarse granularity, limited analysis scale, and narrow focus. |
| Approach: | They propose a framework for analyzing the linguistic mechanisms of large language models based on Sparse Auto-Encoders. |
| Outcome: | The proposed framework extracts Chinese and English linguistic features across four dimensions . it uncovers intrinsic representations of linguistic knowledge in LLMs and can control outputs . |
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) can disentangle complex features into more interpretable components. |
| Approach: | They propose to use Sparse Autoencoders to disentangle LLM features into more interpretable components. |
| Outcome: | The proposed method disentangles complex features into more interpretable components. |
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research. |
| Approach: | They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them. |
| Outcome: | The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions. |
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models (2025.acl-demo)
Copied to clipboard
Jiaxiang Liu, Boxuan Xing, Chenhao Yuan, ChenxiangZhang ChenxiangZhang, Di Wu, Xiusheng Huang, Haida Yu, Chuhan Lang, Pengfei Cao, Jun Zhao, Kang Liu
| Challenge: | Existing interpretation methods only support tasks with specific inputs, limiting their practical applications. |
| Approach: | They propose an extensible module that matches different input data with interpretation methods and consolidates the interpreting outputs. |
| Outcome: | The proposed module can match different input data with interpretation methods and consolidate the interpreting outputs. |
Computation Mechanism Behind LLM Position Generalization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have explored how LLMs handle positional relevance, but how they handle it remains unexplored. |
| Approach: | They propose to enforce certain computational mechanisms to allow for the tolerance in position perturbations in large language models (LLMs) they also find a pattern in intermediate features that allows this effect to be observed . |
| Outcome: | The proposed models can understand text with position perturbations and generalize to longer sequences than those seen during training with the latest techniques. |
On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in NLP systems have led to widespread adoption by a broad spectrum of users across various domains, impacting decision-making, the job market, society, and scientific research. |
| Approach: | They examine existing interpretability paradigms, their properties, and their relevance to different stakeholders by analyzing trends from the past decade across multiple research fields. |
| Outcome: | The proposed models are complex and opaque and are often overlooked by technical surveys. |
Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on explainable AI focus on post-hoc explanation methods that interpret trained models through external approximations. |
| Approach: | They propose to categorize existing approaches into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |
| Outcome: | The proposed approaches are categorized into five design paradigms: functional transparency, concept alignment, representational decomposability, explicit modularization, and latent sparsity induction. |