Papers by Jihai Zhang
BC-Prover: Backward Chaining Prover for Formal Theorem Proving (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for interactive theorem proving in formal logic lack robustness and robustness. |
| Approach: | They propose a backward chaining framework guided by pseudo steps for proofstep generation that prioritizes pseudo steps. |
| Outcome: | The proposed framework improves on the miniF2F benchmark. |
I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)
Copied to clipboard
Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang
| Challenge: | Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts. |
| Approach: | They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning . |
| Outcome: | Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics. |
SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on the text modality or are limited to specific tasks. |
| Approach: | They propose a framework to teach Large Vision-Language Models to selectively utilize retrieved information and improve their robustness against irrelevant or misleading references. |
| Outcome: | The proposed framework improves LVLMs’ ability to utilize retrieved multimodal references and their robustness against irrelevant or misleading information. |
Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to Reinforcement Learning (RL) rely on massive static datasets, leading to computational inefficiency and redundant gradient updates. |
| Approach: | They propose a data-centric RL framework that dynamically selects the most informative training samples to optimize RL for mathematical reasoning. |
| Outcome: | The proposed framework achieves comparable performance to full-data training methods while requiring only 1.5K samples instead of 220K, reducing training time from 13 days to just 4 hours on 8A800 GPUs. |
Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion (2025.coling-main)
Copied to clipboard
| Challenge: | Empirical evidence suggests that LLMs perform worse than conventional KGC approaches. |
| Approach: | They propose a filter-then-generate paradigm and a multiple-choice question format to harness the capability of LLMs while mitigating the issue casused by hallucinations. |
| Outcome: | The proposed method achieves substantial performance gain compared to existing state-of-the-art methods. |
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies found that CLIP can only encode one aspect of the feature space, leading to substantial information loss and indistinctive features. |
| Approach: | They propose a model-agnostic approach that fine-tunes complementary CLIP models and transforms them into a CLIP-MoE. |
| Outcome: | The proposed framework fine-tunes a series of complementary CLIP models and transforms them into a CLIP-MoE. |