Papers by Xiaokang Liu

7 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.
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models have been proposed and applied to many NLP tasks, yielding state-of-the-art performance, but high storage and computational costs obstruct them to be effectively deployed on resource-constrained devices and real-time applications.
Approach: They propose a BERT distillation method which allows each intermediate student layer to learn from any intermediate teacher layers.
Outcome: The proposed method can learn from different teacher layers adaptively for different NLP tasks.
PedagogyBench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing video understanding benchmarks do not adequately capture the pedagogical logic embedded in instructional videos.
Approach: They propose a pedagogy-driven segmentation strategy and a dual-stream semantic injection pipeline that combines machine pre-annotation with expert refinement.
Outcome: The proposed model performs well on discriminative tasks but degrades on higher-order pedagogical diagnosis, relying on parametric memory rather than grounded visual perception.
Uncovering and Categorizing Social Biases in Text-to-SQL (2023.acl-long)

Copied to clipboard

Challenge: Existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQl, but these models contain social bias at different rates.
Approach: They propose to use data to map natural language utterances to SQL queries.
Outcome: The proposed model can contain social bias at different rates in the downstream Text-to-SQL task.
KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Copied to clipboard

Challenge: Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach: They propose a framework that decouples epistemic planning from content generation.
Outcome: The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.
Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models have been widely used in NLP, but their social or cultural impact is under-explored.
Approach: They build a dataset consisting of numerous **C**hinese **C*omical **C***rosstalk scripts, which is for a popular Chinese performing art called ‘Xiangsheng’ or ‘’ since 1800s.
Outcome: The proposed approach can generate humor as humans do, but it is still in its infancy.
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%.

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