activity
20242026
collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2026

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

Yu Wang, Shengyao Zhuang, Xueguang Ma +4

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with th…

cs.CL2026

Rethinking On-policy Optimization for Query Augmentation

Zhichao Xu, Shengyao Zhuang, Xueguang Ma +6

Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first pr…

cs.CL2026

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion

Maitrey Mehta, Nishant Subramani, Zhichao Xu +2

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary…

cs.CL2026

InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis

Oliver Bentham, Vivek Srikumar

Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging. Benchmarks derived from published studi…

cs.CL2025

Distillation versus Contrastive Learning: How to Train Your Rerankers

Zhichao Xu, Zhiqi Huang, Shengyao Zhuang +1

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowle…

cs.CL2025

Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning

Atharv Kulkarni, Vivek Srikumar

In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of…