We have 3 of 22 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
A representation-space analysis of RIM and the Safety-Direction Penalty (SDP), which penalizes movement along a learned safety direction during reasoning fine-tuning, is provided, which restores safety while preserving benchmark reasoning performance.
SFAD is presented, a speculative decoding framework that enhances contextual faithfulness without inference degradation and substantially improves faithfulness while achieving $2.48\times$ speedup, offering a practical solution for efficient LLMs.
These results show that evaluating only a final checkpoint can obscure both when counterfactual responsiveness changes and what the latent states contribute, and show that high task accuracy can coexist with low counterfactual responsiveness.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
