Hugging Face Trending Papers
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
3d ago
BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing
arXiv:2608.31105v1 Announce Type: new Abstract: Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of...
arXiv AI
Jun 30
Most Current Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.
arXiv AI
2d ago
Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary Search
arXiv:2609.00652v1 Announce Type: new Abstract: Language model agents increasingly propose actions, observe external feedback, and explain their own behavior. Their confidence and rationales are conv...
arXiv AI
Jun 19
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
arXiv Machine Learning
Jul 1
White-Box Sensitivity Auditing with Steering Vectors
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv AI
Aug 12
Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.