Circuits in Language Models

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

All topics

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
May 7, 2026Hang Chen, Jiaying Zhu, Hongyang Chen +3Supervised Fine-Tuning Transformer Interpretability
School of Computer Science and Technology Xi’an Jiaotong University · School of Computer Science and Engineering The Chinese University of Hong Kong · Shaanxi Co., Ltd(Xi’an 710077, China) China Mobile Group +1
CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt
May 7, 2026Md Touhidul Islam, Sujan Kumar Saha, Farimah Farahmandi +1Electronic Design Automation Language Modeling
University of Florida
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Apr 30, 2026Hongliang Liu, Tung-Ling Li, Yuhao WuLLM Interpretability Mechanistic Interpretability
Palo Alto Networks
Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
Apr 27, 2026Shun Shao, Binxu Wang, Shay B. Cohen +2LLM Interpretability Mechanistic Interpretability
University of Cambridge · Kempner Institute, Harvard University · University of Edinburgh +1
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
Apr 21, 2026Manav PandeyLLM Sycophancy LLM Alignment
Georgia Institute of Technology
A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation
Apr 16, 2026Yuval Ran-Milo, Hila Ofek, Shahar MendelSelf-Attention Decoder-Only Language Models
Tel Aviv University
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
Apr 9, 2026Stephen Cheng, Sarah Wiegreffe, Dinesh ManochaLanguage Model Steering LLM Interpretability
University of Maryland, College Park
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Apr 6, 2026Gregory N. FrankLLM Interpretability LLM Safety
Chief Scientist, Molt AI Corp.
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
Jan 21, 2026Injin Kong, Hyoungjoon Lee, Yohan JoMasked Diffusion Models Autoregressive Diffusion
Graduate School of Data Science, Seoul National University · Department of Biosystems & Biomaterials Science and Engineering, Seoul National University

May 7, 2026, cs.CLJ/K move · Enter open · S save

Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training

Hang Chen, Jiaying Zhu, Hongyang Chen, Hongxu Liu+2

School of Computer Science and Technology Xi’an Jiaotong University · School of Computer Science and Engineering The Chinese University of Hong Kong · Shaanxi Co., Ltd(Xi’an 710077, China) China Mobile Group+1

Supervised Fine-Tuning Transformer Interpretability LLM Interpretability Mechanistic Interpretability Circuits in Language Models LLM Post-Training+1

Open paper AskPDF arXiv

The "Locate-then-Update" paradigm has become a predominant approach in the post-training of large language models (LLMs), identifying critical components via mechanistic interpretability for targeted parameter updates. However, this paradigm rests on a fundamental yet unverified assumption: can mechanisms derived from current static parameters reliably guide future dynamic parameter updates? To investigate this, we systematically track the structural evolution of Transformer circuits throughout the supervised fine-tuning (SFT) process, revealing the underlying dynamics of task mechanisms. We introduce three novel metrics-Circuit Distance, Circuit Stability, and Circuit Conflict-to analyze circuit evolution across three dimensions: neural migration, semantic stability, and cross-task interference. Our empirical results reveal that circuits inherently exhibit "Free Evolution" during parameter updates. Consequently, static mechanisms extracted from current states inevitably suffer from temporal latency, making them fundamentally inadequate for guiding future states. Moreover, by deconstructing the "illusion of effectiveness" in existing methods, this work underscores the necessity of "foresight" in mechanistic localization and proposes a predictive framework for future research.

Momentum

Related topics

Latest papers 69