activity
20242026
collaborators

7 papers

cs.CL2026

Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters

Lifu Tu, Yingbo Zhou, Semih Yavuz

Training effective multilingual embedding models presents unique challenges due to the diversity of languages and task objectives. Although small multilingual models (<1 B paramete…

cs.CL2026

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

Yiyang Shen, Lifu Tu, Weiran Wang

Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiab…

cs.CL2026

LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings

Lifu Tu, Rongguang Wang, Tao Sheng +2

Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conv…

cs.CL2025

Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown

Lifu Tu, Rui Meng, Shafiq Joty +2

Large language models (LLMs) have demonstrated strong capabilities in text understanding and generation. However, they often lack factuality, producing a mixture of true and false…

cs.CL2024

AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation

Rui Meng, Ye Liu, Semih Yavuz +6

Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-anno…

cs.CL2024

Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding

Lifu Tu, Semih Yavuz, Jin Qu +4

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, esp…