collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away

Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh +3

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But re…

cs.CL2025

Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models

Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande +2

Large language models are increasingly used for creative writing and engagement content, raising safety concerns about the outputs. Therefore, casting humor generation as a testbed…

cs.CL2025

Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples

Soumya Suvra Ghosal, Vaibhav Singh, Akash Ghosh +4

Reward models are essential for aligning large language models (LLMs) with human preferences. However, most open-source multilingual reward models are primarily trained on preferen…

cs.CL2025

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time

Mohamad Chehade, Soumya Suvra Ghosal, Souradip Chakraborty +4

Aligning large language models with humans is challenging due to the inherently multifaceted nature of preference feedback. While existing approaches typically frame this as a mult…

cs.CL2025

Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag +7

Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effect…