Unlocking Multilingual Reasoning Capabilities of LLMs and LVLMs via Representation Engineering
Qi-Ming Li, Xiao-Cheng Feng, Yi-Xuan Ma et al.
· 0 citations
2 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.
Disentangling Statistical Preemption from Entrenchment in Language Models'Avoidance of Overgeneralization
How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that describe indirect negative evidence against overgeneralizations: preemption (which privileges exposure to near-synonymous construction---e.g., she made him laugh) vs. ent...
Yi-Xuan Wang, Freda Shi, Kanishka Misra
· 0 citations