This work introduces a solution built on top of FairytaleQA and tailored for training a DeBERTa-based model to classify the quality of each candidate to be part of a strong answer-question pair and proposes three strategies based on semantic similarity and text position to ensure coverage and diversity of candidates’ s...
C. Preda, Mihai Dascalu, Stefan Ruseti et al.· International Conference on...· 0 citations
Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although autoregressive language models are optimized token by token. As a result, all tokens in a rejected response contribute to the negative training signal, including tokens that m...
Andreea Dutulescu, Stefan Ruseti, Mihai Masala et al.· 0 citations
A pilot project in which students in a statistics course within a data science engineering program created culturally diverse multiple-choice questions, generated answers using LLMs, and applied statistical methods to assess model accuracy is presented, supporting a cultural injection hypothesis.
Denis Iorga, Razvan Muntean, Mihai Masala et al.· Electronics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
