5 papers
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
Joschka Braun, Carsten Eickhoff, Seyed Ali Bahrainian
Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. While predominantly studied for…
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Eyon Jang, Damon Falck, Joschka Braun +6
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on suf…
Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
Joschka Braun
Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, stee…
Logit Reweighting for Topic-Focused Summarization
Joschka Braun, Bálint Mucsányi, Seyed Ali Bahrainian
Generating abstractive summaries that adhere to a specific topic remains a significant challenge for language models. While standard approaches, such as fine-tuning, are resource-i…
Understanding (Un)Reliability of Steering Vectors in Language Models
Joschka Braun, Carsten Eickhoff, David Krueger +2
Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising…