260 citations · 703 across the 99 of their papers we have counts for
3 papers · 1 filter
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
Harethah Abu Shairah, Hasan Abed Al Kader Hammoud, George Turkiyyah +1
Safety alignment in Large Language Models (LLMs) often involves mediating internal representations to refuse harmful requests. Recent research has demonstrated that these safety me…
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati +4
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. H…