9 papers
POOL: Propagated Uncertainty Over Lookalikes
Rounak Sharma, Ananya B. Sai, Soumyabrata Pal
Black-box large language models need confidence scores that can separate likely-correct from likely-incorrect outputs, enabling systems to prioritize human review, route uncertain…
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat +3
Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies reveal th…
KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
Vaibhav Singh, Soumya Suvra Ghosal, Kapu Nirmal Joshua +2
In-context learning (ICL) has emerged as a powerful paradigm for adapting large language models (LLMs) to new and data-scarce tasks using only a few carefully selected task-specifi…
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
Kiran Purohit, Ramasuri Narayanam, Soumyabrata Pal
Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its to…
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction
Akriti Jain, Saransh Sharma, Koyel Mukherjee +1
Auto-regressive Large Language Models (LLMs) demonstrate remarkable performance across different domains such as vision and language processing. However, due to sequential processi…
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…