← Search

Shivam Shandilya

2 accepted papers

2025

CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling

ACL 2025finding

Reward modeling in large language models is known to be susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In RLHF, and more generally during post-training, flawed reward signals often lead to outpu…

Cited by 0SourcePDFScholar
2025

TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning

ACL 2025finding

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt compression aims to reduce the inference cost by minimizing input toke…

Cited by 0SourcePDFScholar