Papers by Xin Tan

28 papers
ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods that align natural language with SQL Language underestimate inherent structural characteristics of SQL and lead to structure errors.
Approach: They propose a retrieval-argument framework that aligns natural language with SQL Language and trains one encoder-decoder-based model to fit all questions.
Outcome: The proposed framework improves accuracy and robustness of text-to-SQL generation on five datasets.
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks (2026.acl-long)

Copied to clipboard

Challenge: Existing supervised defense methods rely on labeled malicious agents to train a supervised model of malicious behavior.
Approach: They propose an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.
Outcome: The proposed method detects diverse attack types across MAS with various communication patterns while maintaining superior generalizability compared to baselines.
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation (D19-1)

Copied to clipboard

Challenge: Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context.
Approach: They propose a hierarchical model to learn document context for document-level neural machine translation . they use a sentence encoder to capture intra-sentence dependencies and a document encoder .
Outcome: The proposed model significantly improves document-level translation performance over strong baselines.
A Benchmark for Translations Across Styles and Language Variants (2025.findings-emnlp)

Copied to clipboard

Challenge: lack of comprehensive evaluation benchmarks has hindered progress in this field . lack of evaluation benchmarking has hinder MT's ability to generate accurate outputs .
Approach: They evaluate translations across semantic preservation, cultural and regional specificity, expression style, and fluency at both the word and sentence levels.
Outcome: The proposed evaluation framework is validated on translations of state-of-the-art large language models .
EDTC: A Corpus for Discourse-Level Topic Chain Parsing (2021.findings-emnlp)

Copied to clipboard

Challenge: Discourse analysis is a fundamental part of natural language processing.
Approach: They propose a discourse-level topic chain parsing system which can be automated . they propose lexical cohesion modeling instead of lexically measuring topic structure .
Outcome: The proposed system is robust and reliable, and can provide high reliability and low confidence scores.
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks (2023.findings-acl)

Copied to clipboard

Challenge: Existing work adopts data augmentation techniques to generate pseudo-annotated sentences . existing methods neither preserve semantic consistency of original sentences nor preserve syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
Approach: They propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures.
Outcome: The proposed technique can bring 2.0% F1 improvements in three datasets under low-resource setting.
IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)

Copied to clipboard

Challenge: Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications.
Approach: They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks.
Outcome: The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict.
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.
MixTEA: Semi-supervised Entity Alignment with Mixture Teaching (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to learn informative entity embeddings are insufficient for semi-supervised entity alignment.
Approach: They propose a semi-supervised method which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings.
Outcome: The proposed method is superior to existing methods on benchmark datasets and further analyses.
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Challenge: Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach: They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome: The proposed framework improves performance of commercial and open-source models.
N-ary Constituent Tree Parsing with Recursive Semi-Markov Model (2021.acl-long)

Copied to clipboard

Challenge: Existing graph-based constituent parsing methods generate hidden nodes with the dummy label inside the n-ary nodes to transform the tree into a binary tree for prediction.
Approach: They propose a graph-based constituent parsing framework that uses a 1-order semi-Markov model to predict the immediate children sequence of a constituent candidate.
Outcome: The proposed framework obtains the F1 of 95.92% and 92.50% on the datasets of PTB and CTB 5.1 respectively.
Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach: They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome: The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing detection methods fail to account for **self-consistent error** . study identifies self-consistency errors and evaluates them .
Approach: They propose a method that fuses hidden state evidence from an external verifier LLM to detect self-consistent errors.
Outcome: The proposed method significantly enhances performance on self-consistent errors across three LLM families.
NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms.
Approach: They propose a visual-target trajectory collection pipeline that generates trajectories for GUI and embodied tasks using a single formulation.
Outcome: The proposed agent outperforms state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation.
Improving Explainable Fact-Checking with Claim-Evidence Correlations (2025.coling-main)

Copied to clipboard

Challenge: Existing fact-checking systems that employ large language models fail to reveal reasoning principles behind their decision-making for the claim verdict.
Approach: They propose an LLM-based fact-checking system that simulates human reasoning principles . they propose a test set to evaluate the CorXFact system in real-world and closed-domain scenarios .
Outcome: The proposed system outperforms four strong fact-checking baselines in claim authenticity prediction and verdict explanation.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models exhibit remarkable generative capabilities but can be misused for harmful purposes.
Approach: They propose a framework that transforms natural language inputs into code inputs.
Outcome: The proposed framework bypasses the safety guardrails of all models more than 80% of the time.
SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Copied to clipboard

Challenge: Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach: They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome: SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .
Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods lack explainability and generalization, making it difficult to justify inference decisions and detect implicit sentiment across domains and varied expression patterns.
Approach: They propose an explainable multi-path tree-guided chain-of-thought framework specifically designed for ASQP.
Outcome: Experiments on benchmark datasets show that Tree-CoT-RT outperforms baselines.
CrystalICL: Enabling In-Context Learning for Crystal Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for crystal generation are limited to zero-shot scenarios and are unable to benefit from few-shot situations.
Approach: They propose a model designed for few-shot crystal generation that exploits in-context learning by capturing structure-property relationships from limited data.
Outcome: The proposed model reduces complexity of modeling crystal symmetry in LLMs and exploits ICL by capturing structure-property relationships from limited data.
HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification.
Approach: They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models.
Outcome: The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets.
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries.
Approach: They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios.
Outcome: The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities.
Template-free Prompt Tuning for Few-shot NER (2022.naacl-main)

Copied to clipboard

Challenge: Prompt-based methods have been successfully applied in few-shot learning tasks . however, when applied to token-level labeling tasks, it would be time-consuming to enumerate the template queries over all potential entity spans.
Approach: They propose a method to reformulate NER tasks as LM problems without templates.
Outcome: The proposed method is 30.12 times faster than the template-based method under few-shot settings.
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Copied to clipboard

Challenge: a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach: They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome: The proposed benchmarks show that the current models perform worse than the human ceiling.
BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Copied to clipboard

Challenge: Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach: They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome: The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines.
Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation (2021.emnlp-main)

Copied to clipboard

Challenge: ZP-annotated natural language generation (NLG) corpora are scarce in pro-drop languages . despite efforts to bridge the discrepancy between human and machine, zero pronouns still persist in pro -drop tasks.
Approach: They propose a highly adaptive two-stage approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks.
Outcome: The proposed approach can improve translation, question answering, and summarization tasks.
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.
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, leading to fragmented memories and unstable long-horizon personalization.
Approach: They propose a temporal–hierarchical memory framework that organizes conversations through a Temporal Memory Tree.
Outcome: The proposed framework outperforms baselines while reducing the recalled memory length by 52.20%.
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems (2025.emnlp-main)

Copied to clipboard

Challenge: Empirical studies for communication topology design often overlook why and when sparse and dense topologies help or hinder collaboration.
Approach: They propose a topology design approach that balances error suppression and beneficial information propagation by fusing connectivity patterns from dense and sparse graphs.
Outcome: The proposed topology design achieves superior performance across tasks with sparse and dense graphs.

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