Papers by Xiaokang Zhang

12 papers
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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations