Papers by Qiao Xiao

8 papers
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach: They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome: The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition models are feature-engineering and machine learning based.
Approach: They propose a new NER learning framework that uses entity mentions to improve model performance.
Outcome: The proposed model achieves better performance on OOV entities on various settings and datasets.
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)

Copied to clipboard

Challenge: Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention.
Approach: They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents.
Outcome: The proposed model achieves a high 96% F1 score on data quality and is far lower than humans.
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction (2026.acl-long)

Copied to clipboard

Challenge: Currently, knowledge graphs are decoupled from their downstream application, resulting in suboptimal graph structures.
Approach: They propose a framework to directly optimize KG construction for task performance using Reinforcement Learning (RL).
Outcome: The proposed framework improves performance across multiple QA benchmarks and consistently achieves significant performance gains over task-agnostic baseline graphs.
MedCite: Can Language Models Generate Verifiable Text for Medicine? (2025.findings-acl)

Copied to clipboard

Challenge: Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice.
Approach: They propose a framework that facilitates the design and evaluation of LLM citations for medical tasks and a retrieval-citation method that generates high-quality citation.
Outcome: The proposed method achieves superior citation precision and recall improvements compared to strong baseline methods and correlates well with annotation results from professional experts.
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Challenge: a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach: They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome: The proposed agents are based on operating systems (OS) and operating systems frameworks.
A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-making (2025.emnlp-main)

Copied to clipboard

Challenge: Medical decision-making often involves integrating knowledge from multiple clinical specialties. static, pre-assigned roles hinder adaptability and dynamic knowledge integration.
Approach: They propose a Knowledge-driven Adaptive Multi-Agent Collaboration framework that emulates large language models to emulate expert teamwork.
Outcome: The proposed framework outperforms single-agent and advanced multi-agend methods on two real-world medical scenarios.
DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to test-time adaptation of vision-language models measure prediction entropy but these samples tend to approach prototypes with limited coverage of data distributions.
Approach: They propose a new approach for test-time adaptation of vision-language models . they construct a dynamic cache to store diversity-aware test samples .
Outcome: The proposed approach is more efficient than current methods on augmented visual models.

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