Papers by Xiaokang Zhang
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL (2025.acl-long)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) is effective in complex reasoning tasks like math word problems and code generation, but Text-to-SQL datasets often include only final answers (gold SQL queries) without detailed CoT solutions. |
| Approach: | They found that Direct Preference Optimization (DPO) is crucial for unlocking DPO's potential by augmenting Text-to-SQL datasets with synthetic CoT solutions. |
| Outcome: | The proposed method achieves consistent and significant performance improvements on Text-to-SQL datasets. |
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026.acl-long)
Copied to clipboard
Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang
| Challenge: | Existing methods for storing key-value caches during long-horizon rollouts cause performance collapses. |
| Approach: | They propose a new training paradigm that empowers stable RL training under sparse rollouts. |
| Outcome: | The proposed model reduces rollout overhead while maintaining the performance. |
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering (2022.acl-long)
Copied to clipboard
| Challenge: | Existing retrieval methods for knowledge base question answering are either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs. |
| Approach: | They propose a subgraph retrieval framework that decouples the retrieval from the subsequent reasoning process and trains subgraphs for easier reasoning. |
| Outcome: | The proposed framework improves retrieval and QA performance over existing methods. |
ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry (2026.acl-long)
Copied to clipboard
| Challenge: | Experimental protocols in organic synthesis specify not only the intended transformation, but also an executable sequence of operations and conditions. |
| Approach: | They propose a human-validated benchmark for verifiable experimental procedure reasoning . they instantiate 7306 benchmark tasks across six complementary formats . |
| Outcome: | The proposed benchmarks show that the evaluations are less diagnostic of procedure-level decision making. |
HOSMEL: A Hot-Swappable Modularized Entity Linking Toolkit for Chinese (2022.acl-demo)
Copied to clipboard
| Challenge: | Existing studies have explored the use of entity linking (EL) in downstream tasks. |
| Approach: | They propose a modularized entity linking toolkit for easy task adaptation. |
| Outcome: | The proposed toolkit achieves significantly better accuracy and less time and spaceconsumption than existing methods. |
Dynamic Scaling of Unit Tests for Code Reward Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing large language models struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. |
| Approach: | They propose a lightweight yet effective unit test generator that scales unit tests based on problem difficulty. |
| Outcome: | The proposed approach significantly improves performance on three benchmarks. |
Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking (2024.acl-long)
Copied to clipboard
| Challenge: | Existing factuality detection methods are not effective for large language models (LLMs). |
| Approach: | They propose a probing model that trains on offline consistency checking results. |
| Outcome: | The proposed model reduces the computational burden of generating multiple responses by online consistency verification and improves on factuality detection and question answering benchmarks. |
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios (2025.findings-acl)
Copied to clipboard
Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, Daniel Zhang-Li, Jifan Yu, Shu Zhao, Juanzi Li, Jie Tang
| Challenge: | TableLLM is a robust large language model capable of handling tabular data manipulation tasks. |
| Approach: | They propose a distant supervision method for training which includes a reasoning process extension strategy and a cross-way validation strategy. |
| Outcome: | The proposed model has 8 billion parameters and is capable of handling tabular data tasks. |
CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing inference scaling methods rely heavily on the quality of candidate responses . however, they are unable to produce correct answers when all candidates are flawed . |
| Approach: | They propose a CoT-based inference scaling strategy that leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses. |
| Outcome: | The proposed method improves performance on four benchmark datasets with seven policy models. |
ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for extracting chemical procedures from literature are insufficient and low-quality due to the inherent ambiguity of chemical language and the high cost of human annotation. |
| Approach: | They propose a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences. |
| Outcome: | The proposed model outperforms the baseline model on R2D and D2A tasks by 10%. |
SAM Decoding: Speculative Decoding via Suffix Automaton (2025.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) methods are inefficient and rely on single retrieval resources. |
| Approach: | They propose a retrieval-based speculative decoding method that adapts the suffix automaton for efficient draft generation by utilizing the generating text sequence and static text corpus. |
| Outcome: | The proposed method can find the longest suffix match and can be integrated with existing methods to generalize to broader domains. |
P2 Law: Scaling Law for Post-Training After Model Pruning (2025.acl-long)
Copied to clipboard
| Challenge: | Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). |
| Approach: | They propose to use model pruning techniques to maintain high performance while reducing hardware requirements for large language models (LLMs). |
| Outcome: | The proposed model pruning law can be generalized to larger dataset sizes, larger model sizes, and higher pruning rates, offering valuable insights for resource allocation in pruned LLMs. |