6 papers
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…
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…
From Selection to Generation: A Survey of LLM-based Active Learning
Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie +31
Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent…
PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks
Soumya Suvra Ghosal, Soumyabrata Pal, Koyel Mukherjee +1
Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on…
Sparse Linear Bandits with Blocking Constraints
Adit Jain, Soumyabrata Pal, Sunav Choudhary +3
We investigate the high-dimensional sparse linear bandits problem in a data-poor regime where the time horizon is much smaller than the ambient dimension and number of arms. We stu…
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…