Xiaotang Du

I am a PhD student at the University of Edinburgh, supervised by Pasquale Minervini, Emily Allaway and Ivan Titov. I am part of the Meaning Language and Explainability (MLE) Lab. Broadly, my research focuses on improving the trustworthiness of LLMs in complex knowledge intensive tasks, with a particular interest in making the reasoning process explainable, grounded, and verifiable.

Previously, I worked as an AI resident at Meta AI under the supervision of Fabio Petroni, where I developed a generative framework for entity tagging that can extract entities without mention supervision. I completed my MSc in Computer Science at ETH Zurich, advised by Shuhang Gu, working on image restoration and enhancement.

News

Jan 04, 2026	Our paper on analyzing LLM instruction optimization for tabular fact verification has been accepted to EACL Findings 2026!
Oct 25, 2025	Enhancing Long Document Long Form Summarisation with Self-Planning has been accepted to AACL 2025 (Oral)!

Selected Publications

EACL

Analyzing LLM Instruction Optimization for Tabular Fact Verification

Xiaotang Du, Giwon Hong, Wai-Chung Kwan, and 4 more authors

In Findings of the Association for Computational Linguistics: EACL 2026, Mar 2026

Abs DOI PDF

Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first systematic comparison of instruction optimization, based on the DSPy optimization framework, for tabular fact verification. We evaluate four out-of-the-box prompting techniques that cover both text-only prompting and code use: direct prediction, Chain-of-Thought (CoT), ReAct with SQL tools, and CodeAct with Python execution. We study three optimizers from the DSPy framework—COPRO, MiPROv2, and SIMBA—across four benchmarks and three model families. We find that instruction optimization consistently improves verification accuracy, with MiPROv2 yielding the most stable gains for CoT, and SIMBA providing the largest benefits for ReAct agents, particularly at larger model scales. Behavioral analyses reveal that SIMBA encourages more direct reasoning paths by applying heuristics, thereby improving numerical comparison abilities in CoT reasoning and helping avoid unnecessary tool calls in ReAct agents. Across different prompting techniques, CoT remains effective for tabular fact checking, especially with smaller models. Although ReAct agents built with larger models can achieve competitive performance, they require careful instruction optimization.
AACL

Enhancing Long Document Long Form Summarisation with Self-Planning

Xiaotang Du, Rohit Saxena, Laura Perez-Beltrachini, and 2 more authors

In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Dec 2025

Abs DOI PDF

We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability and faithfulness of generated summaries. Our framework applies self-planning methods to identify important content and then generates a summary conditioned on the plan. We explore both an end-to-end and two-stage variants of the approach, finding that the two-stage pipeline performs better on long and information-dense documents. Experiments on long-form summarisation datasets demonstrate that our method consistently improves factual consistency while preserving relevance and overall quality. On GovReport, our best approach has improved ROUGE-L by 4.1 points and achieves about 35% gains in SummaC scores. Qualitative analysis shows that highlight-guided summarisation helps preserve important details, leading to more accurate and insightful summaries across domains.