arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
By Jianhui Chen, Yuzhang Luo, Liangming Pan
arXiv:2606. 12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata.
By Leon Bergen, Usha Bhalla, Sidharth Baskaran, Max Loeffler, Raphael Sarfati, Dhruvil Gala, Ryan Panwar, Santiago Aranguri, Thomas Fel, Atticus Geiger, Matthew Kowal, Siddharth Boppana, Daniel Balsam, Owen Lewis, Jack Merullo, Thomas McGrath, Ekdeep Singh Lubana
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur
arXiv:2608. 03201v1 Announce Type: new Abstract: Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs.
By Yu Feng, Chunting Zang, Chen Shen, Rui Miao, Ge Teng, Weidong Cai, Jieping Ye
arXiv:2608. 10537v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc.
By Chuqiao Lin, Shivaji Sondhi, Xiao-Liang Qi
Matryoshka Attribution (MAttr) is a mask‑learning method that identifies nested subsets of a language model’s internal components by minimizing downstream loss. It uses a differentiable sigmoid top‑k operator and randomizes sparsity during training to produce an attribution ordering of components. MAttr tops the Mechanistic Interpretability Benchmark leaderboard and can be applied via reinforcement learning to pinpoint weight changes that control behaviors such as refusal in Llama 3.1 8B Instruct, where restoring just 1% of weights removes refusals while preserving capabilities.
By Aryaman Arora, Kirill Acharya, Nathan Hu, Yanzhe Zhang, Noah Goodman, Dan Jurafsky, Christopher Potts