Papers by Shengjie Zhang
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning . however, the recipe introduces a significant risk of capability regression, where models forget foundational skills after prolonged training without employing regularization strategies. |
| Approach: | They propose a replay strategy with dynamic objective reweighting for general knowledge preservation using short-horizon signals of convergence and instability. |
| Outcome: | The proposed method preserves general capabilities and improves reasoning . it can be applied to existing RLVR pipelines without training additional models or tuning . |
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang
| Challenge: | Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps. |
| Approach: | They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level. |
| Outcome: | Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models. |
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents (2024.acl-long)
Copied to clipboard
| Challenge: | Xi et al., 2023) show that LLM-based intelligent agents are vulnerable to backdoor attacks. |
| Approach: | They propose to build LLM-based intelligent agents using trained LLMs and fine-tune them on data for the agent task. |
| Outcome: | The proposed methods are robust even after fine-tuning on trusted data. |
BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized various domains with their remarkable capabilities, but their massive parameter sizes pose significant challenges for fine-tuning and inference. |
| Approach: | They propose a Bayesian Knowledge Distillation framework for compact Large Language Models in resource-constrained fine-tuning scenarios that employs Logits Dual-Scaling, Knowledge Alignment Module, and Bayes Distillations Optimization. |
| Outcome: | The proposed framework outperforms baseline methods on various state-of-the-art LLMs, including LLaMA, Qwen2, Bloom, and Vicuna. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |