1 citations · 1 across the 11 of their papers we have counts for
12 papers
LLM Judge Validation Under Sparse Overlap: From Inference to Design
Junxuan Li, Arko Mukherjee, Soumyabrata Pal
Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this overlap sparsi…
Online Learning with LLM Experts from Limited Feedback
Wang Wei, Soumyabrata Pal, Koyel Mukherjee +4
We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We formulate it as a bandit prob…
Instruction Distillation: Text Instructions as Visual Examples
Hardik Jindal, Soumyabrata Pal, Sayak Ray Chowdhury
Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved image example consumes severa…
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…
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…
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…
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…