Papers by Xin Guan
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs (2025.findings-naacl)
Copied to clipboard
Navya Jain, Zekun Wu, Cristian Enrique Munoz Villalobos, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Emre Kazim, Philip Colin Treleaven
| Challenge: | Methods like prompt-based In-Context Knowledge Editing and gradient-based Model Editor Networks (MEND) show irregularity and variability; IKE depends on the prompt, leading to variability and sensitivity; MEND yields inconsistent and gibberish outputs. |
| Approach: | They employ Opinion QA Based Parameter-Efficient Fine-Tuning (PEFT) to manipulate the Big Five personality traits: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. |
| Outcome: | The proposed methods show that they are more accurate than prompt-based IKE and gradient-based MEND outputs. |
Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA (2024.acl-long)
Copied to clipboard
Yue Fan, Jing Gu, Kaiwen Zhou, Qianqi Yan, Shan Jiang, Ching-Chen Kuo, Yang Zhao, Xinze Guan, Xin Wang
| Challenge: | Multipanel images are a common form of visual representations, and humans can achieve approximately 99% accuracy on these questions. |
| Approach: | They propose a benchmark that tests multipanel visual reasoning models with 6,600 triplets of questions, answers, and multipanel images. |
| Outcome: | The proposed benchmark features 6,600 triplets of questions, answers, and multipanel images that challenge state-of-the-art Multimodal Large Language Models (MLLMs) human users can attain approximately 99% accuracy on these questions, compared with previous benchmarks. |
JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing automated ICD coding systems face several fundamental challenges due to the limited availability of publicly available Chinese ICD datasets. |
| Approach: | They propose to use a Chinese ICD coding dataset and a multi-agent framework to reformulate ICD as a joint disease-procedure coding task. |
| Outcome: | The proposed system outperforms state-of-the-art methods on real-world Chinese ICD coding datasets and 1.7B-parameter models. |
MAGRET: Machine-generated Text Detection with Rewritten Texts (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies focus on detecting machine-generated text in open-source models, but their performance on closed-source large models is limited. |
| Approach: | They propose a method to detect rewritten text from large language models using a BERT encoder and propose to refine it to achieve semantic alignment. |
| Outcome: | The proposed method outperforms baseline methods on three text-generated datasets. |
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Evidence-Augmented Policy Optimization (EAPO) improves long-context reasoning performance . Xu et al., 2025): large language models are a critical part of NLP . |
| Approach: | They propose an Evidence-Augmented Reasoning paradigm that uses a group-relative reward to improve evidence quality. |
| Outcome: | EAPO significantly improves long-context reasoning performance compared to baselines. |
HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications (2025.naacl-industry)
Copied to clipboard
Rishi Kalra, Zekun Wu, Ayesha Gulley, Airlie Hilliard, Xin Guan, Adriano Koshiyama, Philip Colin Treleaven
| Challenge: | Large Language Models (LLMs) face limitations due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. |
| Approach: | They propose a Hybrid Parameter-Adaptive RAG system for the AI legal domain with NYC Local Law 144 as the test case. |
| Outcome: | The proposed system improves retrieval accuracy, response fidelity, and contextual precision on NYC Local Law 144 . Empirical evidence indicates that many AI tools overstate their ability to prevent hallucinations in legal and policy contexts. |
Self-Supervised Sentence Polishing by Adding Engaging Modifiers (2023.acl-demo)
Copied to clipboard
| Challenge: | a typical way to polish sentences is to add engaging modifiers, which enhance the meaning of the sentence. |
| Approach: | They propose a task that requires polishing sentences while maintaining fluency . they remove engaging modifiers from public resources and fine-tune LongLM to reconstruct original sentences from corrupted ones. |
| Outcome: | The proposed model generates more engaging sentences with suitable modifiers than strong baselines while keeping fluency. |
CEPT: A Contrast-Enhanced Prompt-Tuning Framework for Emotion Recognition in Conversation (2024.lrec-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversation research suffers from data imbalance and the presence of similar linguistic expressions for different emotions. |
| Approach: | They propose a Contrast-Enhanced Prompt-Tuning framework that transforms an ERC task into a Masked Language Modeling task and generates the emotion for each utterance in the conversation. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on all three benchmark datasets and excels in recognizing minority emotions. |
Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points. |
| Approach: | They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot. |
| Outcome: | The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems. |
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption. |
| Approach: | They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval. |
| Outcome: | Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy. |
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries (2025.acl-srw)
Copied to clipboard
Zekun Wu, Seonglae Cho, Umar Mohammed, Cristian Enrique Munoz Villalobos, Kleyton Da Costa, Xin Guan, Theo King, Ze Wang, Emre Kazim, Adriano Koshiyama
| Challenge: | Open-source AI libraries present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. |
| Approach: | They propose a system that leverages large language models and agentic workflows to perform deep, evidence-based evaluations of open-source AI libraries. |
| Outcome: | The proposed system covers up to 88% of OpenSSF Scorecard checks and uncovers 19 additional risks per library. |
SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration (2025.coling-main)
Copied to clipboard
Xin Guan, Nate Demchak, Saloni Gupta, Ze Wang, Ediz Ertekin Jr., Adriano Koshiyama, Emre Kazim, Zekun Wu
| Challenge: | Existing benchmarks for large language models fail to detect bias due to limited scope, contamination, and lack of a fairness baseline. |
| Approach: | They propose a benchmarking pipeline to detect biases in large language models . they use metrics for max disparity, impact ratio, and bias concentration to analyze disparity . |
| Outcome: | SAGED(bias) is the first holistic benchmarking pipeline to address biases in large language models. |
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models generate costly yet semantically void reasoning on beyond-capability tasks . the dominant failure mode is specious reasoning, superficially valid outputs with subtle hallucinations . |
| Approach: | They propose a capability-aligned reinforcement learning approach that aligns model behavior with capability boundaries. |
| Outcome: | The proposed model reduces futile reasoning while maintaining performance across tasks. |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
CORN: Co-Reasoning Network for Commonsense Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work uses two independent modules to model QA content and external commonsense knowledge graph (KG) Existing research uses two separate modules to create QA contextual text representations and relationships between QA entities. |
| Approach: | They propose a commonsense question answering (QA) model that uses two independent modules to model QA contextual text representation and relationships between QA entities in KG. |
| Outcome: | The proposed model achieves state-of-the-art on QA benchmarks in the CommonsenseQA and OpenBookQA datasets. |
JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models (2024.findings-emnlp)
Copied to clipboard
Ze Wang, Zekun Wu, Xin Guan, Michael Thaler, Adriano Koshiyama, Skylar Lu, Sachin Beepath, Ediz Ertekin, Maria Perez-Ortiz
| Challenge: | a framework for benchmarking hierarchical gender hiring bias in Large Language Models (LLMs) is developed to protect vulnerable demographic groups. |
| Approach: | They propose a framework for benchmarking hierarchical gender hiring bias in Large Language Models for resume scoring. |
| Outcome: | The proposed framework reveals significant issues of reverse gender hiring bias and overdebiasing in ten state-of-the-art LLMs. |
Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior . |
| Approach: | They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors. |
| Outcome: | The proposed model can be used to control large language models without architectural modifications. |