Hugging Face Trending Papers June 10, 2026

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

Read the original on Hugging Face Trending Papers →

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. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

safety

arXiv Machine Learning

Jun 11

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

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

safety

arXiv AI

Aug 12

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.

By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jul 2

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.

By Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere, Nikita Menon, Stefan Heimersheim

llms reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Aug 11

Scaling Inherently Interpretable Language Models

arXiv:2608. 07594v1 Announce Type: cross Abstract: Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods whose reliability is difficult to establish.

By Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail, Giang Nguyen, Isaac Plant, Muawiz Chaudhary, Nathaniel Monson, Saqib Azim, Zhichen Guo, Julius Adebayo

llms diffusion safety

arXiv AI

Jun 2

Consistency Training while Mitigating Obfuscation via Rate Matching

arXiv:2606. 02211v1 Announce Type: cross Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer.

By Sohaib Imran, Prakhar Gupta, Jannes Elstner, David Demitri Africa

llms safety

arXiv AI

Jun 6

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.

By Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke Poech

llms safety

Related stories

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

Scaling Inherently Interpretable Language Models

Consistency Training while Mitigating Obfuscation via Rate Matching

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs