Himanshu Beniwal
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
NLP×2AI×2ML×1
Frequent co-authors
Research Timeline
2026
DEPART: DEcomposing PARiTy across Multilingual LLMs
The paper introduces a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
The paper introduces retraining-free frameworks (Meow2X and TRNE) that mechanistically localize and suppress toxicity within language models by analyzing activation differences, achieving safety improvements without costly retraining.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIRecentMay 27, 2026
DEPART: DEcomposing PARiTy across Multilingual LLMs
The paper introduces a diagnostic framework to decompose multilingual LLM performance variance, showing that language identity and model-benchmark interactions are key drivers of performance gaps.
View →
cs.CLcs.AIcs.LGRecentMay 27, 2026