4 papers indexed here
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.
This work investigates how fine-tuning alters internal representations in LLMs, including attention patterns and layer-wise activations, and examines whether these changes are linked to task-relevant components identified by EAP that drive task performance.
It is found that providing candidate senses, similar to what is done in traditional WSD, improves WiC performance in all settings and helps models make more consistent and targeted judgements.
Experimental results show that LLMs exhibit social bias even in coherent, response-conditioned multi-turn interactions, revealing late-emerging bias, non-monotonic bias patterns, and bias re-emergence, which motivate evaluations that extend beyond fixed-turn, pre-scripted protocols.
This work proposes CAROT (Cross-Lingual Alignment of Representations in a Language-Agnostic Space via Optimal Transport), which consists of identifying language-specific representations in LLMs'internal states and aligning language-agnostic representations across languages at the token level by optimal transport, while...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
