6 papers
Disentangling Robustness and Sycophancy in Multilingual LLMs
Rhitabrat Pokharel, Ameeta Agrawal
When a multilingual LLM agrees with a user's false premise, is it being sycophantic, or does it simply not know better in that language? Current research does not distinguish these…
Cross-Lingual Activation Steering for Multilingual Language Models
Rhitabrat Pokharel, Ameeta Agrawal, Tanay Nagar
Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work attributes this gap…
From Policy to Logic for Efficient and Interpretable Coverage Assessment
Rhitabrat Pokharel, Hamid Reza Hassanzadeh, Ameeta Agrawal
Large Language Models (LLMs) have demonstrated strong capabilities in interpreting lengthy, complex legal and policy language. However, their reliability can be undermined by hallu…
MTQ-Eval: Multilingual Text Quality Evaluation for Language Models
Rhitabrat Pokharel, Ameeta Agrawal
The use of large language models (LLMs) for evaluating outputs is becoming an increasingly effective and scalable approach. However, it remains uncertain whether this capability ex…
CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences
Rhitabrat Pokharel, Yufei Tao, Ameeta Agrawal
Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs.…
Generating Continuations in Multilingual Idiomatic Contexts
Rhitabrat Pokharel, Ameeta Agrawal
The ability to process idiomatic or literal multiword expressions is a crucial aspect of understanding and generating any language. The task of generating contextually relevant con…