collaborators

6 papers

cs.CL2026

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

Pranav Bhandari, Nicolas Fay, Amitava Datta +2

Aligning language models with human preferences often requires optimising multiple behavioural objectives. A practical approach is to apply these objectives sequentially using pref…

cs.CL2026

Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation

Mehwish Nasim, Sanjeevan Selvaganapathy, Neel Ganapathi Sabhahit +6

Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they speak when culture is only im…

cs.CL2026

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs

Pranav Bhandari, Nicolas Fay, Sanjeevan Selvaganapathy +3

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The ne…

cs.CL2026

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models

Pranav Bhandari, Usman Naseem, Mehwish Nasim

Personality steering in large language models (LLMs) commonly relies on injecting trait-specific steering vectors, implicitly assuming that personality traits can be controlled ind…

cs.CL2025

Can LLM Agents Maintain a Persona in Discourse?

Pranav Bhandari, Nicolas Fay, Michael Wise +4

Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs ar…

cs.CL2025

Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires

Pranav Bhandari, Usman Naseem, Amitava Datta +2

Psychological assessment tools have long helped humans understand behavioural patterns. While Large Language Models (LLMs) can generate content comparable to that of humans, we exp…