collaborators

11 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

Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection

Sanjeeevan Selvaganapathy, Mehwish Nasim

We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety alignment (uncensored) compare…

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

Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs

Afrozah Nadeem, Agrima Seth, Mehwish Nasim +1

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to p…

cs.CL2026

They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References

Sahil Tripathi, Gautam Siddharth Kashyap, Mehwish Nasim +3

Meme-based social abuse detection is challenging because harmful intent often relies on implicit cultural symbolism and subtle cross-modal incongruence. Prior approaches, from fusi…