Papers by Chenghao Xiao

17 papers
On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning (2023.findings-acl)

Copied to clipboard

Challenge: Incorporating contrastive learning objectives in sentence representation learning has yielded significant improvements on many sentence-level NLP tasks.
Approach: They aim to examine why contrastive learning works for learning sentence-level semantics . they interpret successes through the geometry of the representation shifts based on isotropy .
Outcome: The proposed model improves on many sentence-level NLP tasks, but it is not well understood why it works.
Effective Distillation of Table-based Reasoning Ability from LLMs (2024.lrec-main)

Copied to clipboard

Challenge: Existing work on table-based reasoning distillation has focused on smaller models with limited performance.
Approach: They propose a table-based reasoning distillation approach to distill LLMs into smaller models . their results show that a 220 million parameter model fine-tuned using distilled data improves performance .
Outcome: The proposed model improves on a scientific table-to-text generation dataset and surpasses specific LLMs.
On the Rigour of Scientific Writing: Criteria, Analysis, and Insights (2024.findings-emnlp)

Copied to clipboard

Challenge: despite its importance, little work exists on modelling rigour in scientific writing . despite widespread use of term, scientific literature lacks definition of rigor .
Approach: They propose a framework to automatically identify and define rigour criteria and assess their relevance in scientific writing.
Outcome: The proposed framework can be tailored to the evaluation of scientific rigour for different areas.
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing medical reasoning datasets are limited in scale and typically rely on incomplete data.
Approach: They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline.
Outcome: The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%.
AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for web scraping suffer from limited adaptability and scalability when faced with a new website.
Approach: They propose a framework that generates web scrapers with large language models and a new executability metric to measure the performance of web scraper generation tasks.
Outcome: The proposed framework can handle diverse web environments more efficiently.
RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Scientific rigour tends to be sidelined in favour of bold statements, leading authors to overstate claims beyond what their results support.
Approach: They propose a multimodal framework that retrieves supporting evidence from a paper and assigns each claim an overstatement score.
Outcome: The proposed framework retrieves supporting evidence from ICLR and NeurIPS papers and assigns each claim an overstatement score.
Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages (2026.acl-short)

Copied to clipboard

Challenge: Existing studies show that performance across low-resource settings is variable, resulting in a significant barrier for the MT community.
Approach: They propose to use FRED Difficulty Metrics to contextualize reported performance across different language pairs to determine whether breakthroughs reported in other contexts are artifacts of benchmark collection.
Outcome: The proposed metrics explain a significant portion of result variability rather than model capability.
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth (2025.emnlp-main)

Copied to clipboard

Challenge: Despite excelling at many natural language processing tasks, large language models fail to grasp the layered semantics of Drivelological text.
Approach: They construct a benchmark dataset of over 1,200+ carefully curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean to examine their Drivelological characteristics.
Outcome: The proposed models lack conceptual understanding and lack conceptual and semantic accuracy.
Analyzing LLMs’ Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations (2025.acl-long)

Copied to clipboard

Challenge: Understanding the knowledge boundaries of Large Language Models (LLMs) is crucial to prevent hallucination, but research on the knowledge boundary perceptions of LLMs has predominantly focused on English.
Approach: They propose a training-free alignment method that effectively transfers knowledge boundary perception ability across languages, thereby helping reduce hallucination risk in low-resource languages.
Outcome: The proposed method reduces hallucination risk in low-resource languages by fine-tuning on bilingual question pair translation.
Length is a Curse and a Blessing for Document-level Semantics (2023.emnlp-main)

Copied to clipboard

Challenge: In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models.
Approach: They propose a document-based contrastive learning framework that is length-agnostic self-reference based on document length.
Outcome: The proposed framework achieves state-of-the-art on the standard information retrieval benchmark.
Understanding the Behaviors of Environment-aware Information Retrieval (2026.acl-long)

Copied to clipboard

Challenge: Recent retrieval-augmented generation approaches have demonstrated strong capability in handling complex queries.
Approach: They propose a branching-based rollout technique that improves training stability . they find different retrievers exhibit distinct optimal query styles .
Outcome: The proposed method improves training stability and improves retrieval-aware systems.
CAST: Corpus-Aware Self-similarity Enhanced Topic modelling (2025.naacl-long)

Copied to clipboard

Challenge: Existing topic modelling methods encode contextual information of documents while ignoring contextual details of candidate centroid words. Existing methods are limited by the contextualization gap.
Approach: They propose a topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset and a self-similarity-based method to filter out less meaningful tokens.
Outcome: The proposed method significantly enhances the coherence and diversity of generated topics, and handles noisy data, outperforming strong baselines.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach: They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome: The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are capable of generating human-like text, but the potential for freely customisable characters remains underexplored.
Approach: They propose a framework which employs Large Language Models to create freely customisable characters through personalised characteristic feature injection.
Outcome: The proposed framework provides valuable insights for developing more accurate and customisable human simulacra.
X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Technical language and templated nature of professional reports hinder patient comprehension and allow models to artificially boost lexical metrics such as BLEU by reproducing common report patterns.
Approach: They propose a layman's RRG framework that leverages layperson-friendly language to enhance patient accessibility and promote robust evaluation and report generation by encouraging models to focus on semantic accuracy over rigid templates.
Outcome: The proposed framework improves model performance with more layman-style data, compared to templated professional language and inflated lexical scores.
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts (2026.tacl-1)

Copied to clipboard

Challenge: Evaluating natural language generation systems is challenging due to the diversity of valid outputs.
Approach: They propose an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions.
Outcome: The proposed method requires only a single evaluation sample and eliminates manual prompt engineering.
Modeling Semantic Compositionality with Sememe Knowledge (P19-1)

Copied to clipboard

Challenge: Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents.
Approach: They propose to incorporate sememes into SC models and employ them in learning multiword expressions.
Outcome: The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge.

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