Papers by Xiao Tan

18 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.
Cross-Lingual Phrase Retrieval (2022.acl-long)

Copied to clipboard

Challenge: Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences.
Approach: They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences.
Outcome: The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training.
Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to learn relations from labeled data overlook task interference in continual learning and memory requirements for different relations.
Approach: They propose a framework to learn new relations from limited labeled data while preserving knowledge about previously learned relations.
Outcome: The proposed framework is more practical and comprehensive for real-world scenarios.
PodAgent: A Comprehensive Framework for Podcast Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing automatic audio generation methods struggle to generate podcast-like audio programs effectively.
Approach: They propose a framework for creating podcast-like audio programs that generates informative topic-discussion content by designing a multi-agent collaboration system, builds a voice pool and uses LLM-enhanced speech synthesis to generate expressive conversational speech.
Outcome: The proposed framework surpasses direct GPT-4 generation in topic-discussion dialogue content, and produces more expressive conversational speech.
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach: They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome: The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .
LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)

Copied to clipboard

Challenge: Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment .
Approach: They propose a method to generate lipid molecules efficiently and actively using deep learning.
Outcome: The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods.
Not The End of Story: An Evaluation of ChatGPT-Driven Vulnerability Description Mappings (2023.findings-acl)

Copied to clipboard

Challenge: Existing data proves that ChatGPT performs no less than humans in text generation and knowledge Q&A.
Approach: They propose to use ChatGPT to map vulnerabilities to common weakness enumeration (CWE), common attack pattern ennumeration and classification (ATT&CK) techniques and other classifications.
Outcome: The proposed method performs better than human experts on many tasks, but it can't replace professional security engineers in vulnerability analysis.
Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to detect causal relationships in unstructured texts ignore trivial knowledge which may prejudice performance.
Approach: They propose a pipeline to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsens graphs.
Outcome: The proposed pipeline integrates reliable task-specific knowledge from commonsense graphs.
TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Prior work has focused on treating subwords as basic units in developing such systems.
Approach: They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome: The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.
FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach: They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome: The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.
PsyMem: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing LLMs (2026.tacl-1)

Copied to clipboard

Challenge: Existing role-playing models rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions.
Approach: They propose a framework that integrates fine-grained psychological attributes and explicit memory control for role-playing.
Outcome: The proposed framework outperforms baseline models in human-likeness and character fidelity.
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B.
Approach: They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation.
Outcome: The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model.
Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies on diversity in large language models focus on the understudied class of fairness and inclusion concern in LLMs.
Approach: They propose a technique to measure diversity in generated responses along people and culture axes by collective-critique and self-voting.
Outcome: The proposed approach outperforms baseline methods and human evaluations with human and automated evaluations.
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates (2023.tacl-1)

Copied to clipboard

Challenge: Named Entity Recognition (NER) has evolved from flat to overlapped and discontinuous . NER is a text recognition task that recognizes mentions that represent entities in text .
Approach: They propose a two-stage span-based framework to solve a unified NER task using two stages . they extract entity spans, classify over all entity span pairs and combine them to train two stages.
Outcome: The proposed framework beats all the current competitive baselines on eight benchmark datasets, obtaining the best performance of unified NER.
Joint Event Extraction with Hierarchical Policy Network (2020.coling-main)

Copied to clipboard

Challenge: Existing work on event extraction (EE) is pipelined or uses a joint structure but does not utilize information interactions among event triggers, event arguments, and argument roles.
Approach: They propose to exploit role information of arguments in an event and devise a Hierarchical Policy Network to perform joint EE.
Outcome: The proposed system outperforms existing methods and is more powerful for sentences with multiple events.
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.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization (D19-1)

Copied to clipboard

Challenge: Existing models for natural language video localization are top-down and bottom-up . however, both approaches suffer several limitations, leading to performance degradation .
Approach: They propose a top-down approach for localizing a natural language description in a video sequence . they propose 'DEnse Bottom-Up Grounding' which uses the temporal boundaries of each video frame .
Outcome: The proposed framework matches the speed of top-down models while surpassing the state-of-the-art 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