Papers by Sitong Wu
Logits-Based Finetuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity. |
| Approach: | They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels. |
| Outcome: | The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models. |
QuickLLaMA: Query-aware Inference Acceleration for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) struggle with capturing long-distance dependencies within sequences to deeply understand semantics. |
| Approach: | They propose a system that captures relevant information within a fixed window size and provides precise answers to queries. |
| Outcome: | The proposed system can read Harry Potter within 30s and accurately answer the questions. |
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026.acl-long)
Copied to clipboard
Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu, Shaozuo Yu, Meng Chu, Wenhu Zhang, Haoru Tan, Jiaya Jia
| Challenge: | Search agents are a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. |
| Approach: | They propose a search agent simulation environment that bootstraps robust search agents using Reinforcement Learning. |
| Outcome: | The proposed model outperforms the web-enhanced ASearcher model by 10.6%. |
TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Current reward models for reinforcement learning (RL) rely on outcome rewards that propagate a single scalar value across all tokens based on final correctness. |
| Approach: | They propose a framework that derives dense token-level supervision from LLMs . they use a multi-granularity calibration mechanism to modulate teacher influence . |
| Outcome: | The proposed framework evaluates teacher reliability across problem-level expertise, trajectory-level discrimination, and token-level confidence. |