Papers by Zixuan Zhang

Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)

Challenge:	Modern large-scale Pre-trained Language Models focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences.
Approach:	They propose a new pre-training objective that enables the model to learn latent types . the objective allows the model a self-supervised way to extract sentence-level keywords .
Outcome:	The proposed model learns interpretable latent type categories without external knowledge and improves downstream tasks.

Copied to clipboard

Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)

Challenge:	Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation.
Approach:	They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior.
Outcome:	Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function.

Copied to clipboard

Yu Lei, Zixuan Wang, Yiqing Feng, Junru Zhang, Yahui Li, Liu Chu, Wang Tongyao, Dongyang Li

Why Does New Knowledge Create Messy Ripple Effects in LLMs? (2024.emnlp-main)

Challenge:	Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness.
Approach:	They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem.
Outcome:	FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments.

Copied to clipboard

Jiaxin Qin, Zixuan Zhang, Chi Han, Pengfei Yu, Manling Li, Heng Ji

IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)

Challenge:	Existing research has focused on post-training knowledge editing (KE) for language models to ensure that knowledge remains accurate and up-to-date.
Approach:	They propose to use a GradSim indicator to detect when and why updated knowledge ripples in language models.
Outcome:	The proposed indicator GradSim shows that LMs that fail to handle ripple effects have low GradSIM.

Copied to clipboard

Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang

Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)

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.

Copied to clipboard

Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang

Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning Representation (2021.acl-long)

Challenge:	Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates.
Approach:	They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters.
Outcome:	The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment.

Copied to clipboard

Zixuan Zhang, Nikolaus Parulian, Heng Ji, Ahmed Elsayed, Skatje Myers, Martha Palmer

SSS: Editing Factual Knowledge in Language Models towards Semantic Sparse Space (2024.findings-acl)

Challenge:	Compared with general natural language texts, sentences from scientific papers usually possess wider contexts between knowledge elements.
Approach:	They propose a novel biomedical Information Extraction model to extract scientific entities and events from English research papers using Abstract Meaning Representation (AMR) they construct a sentence-level knowledge graph from an external knowledge base and encode it to improve the model's understanding of complex scientific concepts.
Outcome:	The proposed model can extract scientific entities and events from scientific literature and improve its understanding of complex scientific concepts.

Copied to clipboard

Huazheng Wang, Haifeng Sun, Jingyu Wang, Qi Qi, Zixuan Xia, Menghao Zhang, Jianxin Liao

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026.acl-long)

Challenge:	Existing methods to modify LMs suffer from sub-optimal locality, where irrelevant neighborhood examples can be adversely influenced.
Approach:	They propose to use a model editing method to modify specific examples in LMs to improve locality and reasoning capability by directing the hidden state of edit example towards spaces where semantics are sparse.
Outcome:	The proposed method improves locality and reasoning capability on two datasets.

Copied to clipboard

Zixuan Weng, Jinghuai Zhang, Kunlin Cai, Ying Li, Peiran Wang, Yuan Tian

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization (2024.findings-naacl)

Challenge:	Existing methods for inference-time steering fail to be effective, utility-preserving and training-efficient due to rigid, one-size-fits-all designs and limited adaptability.
Approach:	They propose a steering framework that decomposes inference-time steering into two stages . they propose 'conditional steering' mechanism that preserves model utility by avoiding unnecessary steering . a 'mixture-of-Steering-Experts' mechanism captures multimodal nature of desired steering behaviors .
Outcome:	The proposed framework outperforms the state-of-the-art methods on safety and truthfulness benchmarks.

Copied to clipboard

Zixuan Zhang, Revanth Gangi Reddy, Kevin Small, Tong Zhang, Heng Ji

Natural Language Interfaces

Challenge:	Open-domain Question Answering (OpenQA) aims at answering factual questions using an external large-scale knowledge corpus.
Approach:	They propose a retrieval-augmented approach to QA that focuses on retrieving relevant knowledge from an external corpus.
Outcome:	The proposed model can generalize to completely different knowledge domains while adapting to updated versions of the same knowledge corpus and switching to completely new knowledge domain.

EVEDIT: Event-based Knowledge Editing for Deterministic Knowledge Propagation (2024.emnlp-main)

Copied to clipboard

Jiateng Liu, Pengfei Yu, Yuji Zhang, Sha Li, Zixuan Zhang, Ruhi Sarikaya, Kevin Small, Heng Ji

Reasoning

Challenge:	Existing knowledge editing approaches only operate on (subject, relation, object) triple . current methods are limited to (substance, relation) triple, causing low confidence in their answers.
Approach:	They propose a task of event-based knowledge editing that pairs facts with event descriptions to improve model confidence.
Outcome:	The proposed method improves model confidence by 55.6% while maintaining the naturalness of generation.

Accelerating LLM Fine-Tuning via Embedding Knowledge Transfer (2026.findings-acl)

Copied to clipboard

Meishu Peng, Ziyue Zhang, Yi Zhang, Pengyang Wang, Zixuan Yuan, Denghui Zhang

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Existing studies on parameter-efficient fine-tuning (PEFT) have produced many state-of-the-art results by adapting LLMs to new tasks, but it requires substantial training data and time to enhance model performance.
Approach:	They propose a parameter-efficient fine-tuning framework which efficiently transfers knowledge from a small expert model to a target large model via embedding layers.
Outcome:	The proposed framework accelerates domain-specific fine-tuning, improves model performance and remains robust across diverse model families and PEFT methods.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

Reasoning

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications (2026.findings-acl)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Jianing Hao, Yuhe Wu, Yuanjian Xu, Shichang Meng, Shuai Yuan, Wei Zeng, Zixuan Wang, Guang Zhang

Reasoning

Challenge:	Existing benchmarks focus on narrow tasks and leave a fundamental question unanswered . Existing models only focus on specific tasks, requiring rigorous reasoning and knowledge .
Approach:	They propose a benchmark to connect theoretical foundations with practical business knowledge and applications.
Outcome:	The benchmark systematically evaluates both open-source and commercial LLMs . it reveals how theoretical knowledge translates into practical performance in business .

Identifying the Achilles’ Heel: An Iterative Method for Uncovering Factual Errors in Large Language Models (2026.findings-acl)

Copied to clipboard

Wenxuan Wang, Yuk-Kit Chan, Zixuan Ling, Shi Juluan, Youliang Yuan, Jen-tse Huang, Yifei Zhang, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing (2026.findings-acl)

Challenge:	Current methods for evaluating LLMs’ veracity are limited by the need for extensive human labor, test data contamination, or limited scope, hindering efficient and effective exposure of errors.
Approach:	They propose a framework that extracts fact triplets to generate diverse question types using rule-based natural language processing techniques.
Outcome:	The proposed framework can trigger factual errors in up to 55% of questions in large LLMs while maintaining coverage of questions.

Copied to clipboard

Dongfang Li, Zixuan Liu, Gang Lin, Baotian Hu, Min Zhang

Green & Sustainable NLP

Challenge:	Existing retrieval-based methods compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning.
Approach:	They propose a method that preserves local semantic coherence through boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality.
Outcome:	The proposed method achieves 3.6 end-to-end inference speedup with negligible degradation in model performance.

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing (2025.acl-long)

Copied to clipboard

Zhenyu Li, Yike Zhang, Tengyu Pan, Yutao Sun, Zhichao Duan, Junjie Fang, Rong Han, Zixuan Wang, Jianyong Wang

Challenge:	Existing context condensing methods cannot accurately understand the full context, as there is a considerable amount of information loss in the condensed process.
Approach:	They propose a framework to extend the fixed context length of any decoder-only LLM by distilling crucial information from long sequences.
Outcome:	The proposed framework extends the fixed context length of any decoder-only LLM, allowing it to focus on relevant information from very long sequences.

COVID-19 Claim Radar: A Structured Claim Extraction and Tracking System (2022.acl-demo)

Copied to clipboard

Manling Li, Revanth Gangi Reddy, Ziqi Wang, Yi-shyuan Chiang, Tuan Lai, Pengfei Yu, Zixuan Zhang, Heng Ji

EventKE: Event-Enhanced Knowledge Graph Embedding (2021.findings-emnlp)

Challenge:	a new system extracts supporting and refuting claims from COVID-19 related news . the system is publicly available at GitHub and DockerHub, with complete documentation.
Approach:	They propose a COVID-19 Claim Radar system that extracts supporting and refuting claims . the system leverages Wikidata as the hub to consolidate coreferential knowledge elements .
Outcome:	The system extracts supporting and refuting claims from COVID-19 pandemic information . it leverages Wikidata as the hub to merge coreferential knowledge elements .

Copied to clipboard

Zixuan Zhang, Hongwei Wang, Han Zhao, Hanghang Tong, Heng Ji

RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor (2023.emnlp-demo)

Challenge:	Experimental results show that events can greatly improve the quality of KG embeddings on multiple downstream tasks.
Approach:	They propose an event-enhanced KG embedding model that incorporates events into KGs . they first incorporate event nodes by building a heterogeneous network with event argument links .
Outcome:	The proposed model incorporates event nodes into the original knowledge graphs . it can be used to fuse event information into the KG embeddings on multiple tasks .

Copied to clipboard

Khanh Duy Nguyen, Zixuan Zhang, Reece Suchocki, Sha Li, Martha Palmer, Susan Windisch Brown, Jiawei Han, Heng Ji

Multimodality

Challenge:	Existing IE tools for atomic events are limited when applied to such complex events.
Approach:	They propose to use event schemas to guide the organization of complex events and to edit hierarchical graphs.
Outcome:	The proposed tool outperforms existing IE visualization tools in both IE result analysis and general model improvements.

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation (2025.acl-industry)

Copied to clipboard

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction (2024.findings-eacl)

Challenge:	Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards.
Approach:	They propose a method to transform a generative MLLM into a multimodal classifier using minimal discriminative training data.
Outcome:	The proposed method improves F1 score by 66.50% over traditional classifiers while requiring only 2% of the fine-tuning data.

Copied to clipboard

Qingyun Wang, Zixuan Zhang, Hongxiang Li, Xuan Liu, Jiawei Han, Huimin Zhao, Heng Ji

You Impress Me: Dialogue Generation via Mutual Persona Perception (2020.acl-main)

Challenge:	Existing frameworks for fine-grained few-shot entity extraction are difficult to implement in the chemical domain due to the information overload of scientific papers.
Approach:	They propose a sequence-to-sequence based few-shot entity extraction approach . it uses a seq2seq entity extractor and a self-validation module to reconstruct original input sentence .
Outcome:	The proposed framework achieves 8.26% and 6.84% performance gains on two datasets.

Copied to clipboard

Qian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou, Zixuan Chen, Bin Zhou, Dongmei Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing chit-chat systems tend to generate uninformative responses and lack coherent personality traits due to the diversity of speakers.
Approach:	They propose a transmitter-receiver framework which explicitly models understanding between interlocutors.
Outcome:	The proposed framework improves on a large public dataset, Persona-Chat, with a significant boost over the state-of-the-art frameworks.

Adam’s Law: Textual Frequency Law on Large Language Models (2026.acl-long)

Copied to clipboard

Hongyuan Lu, Zixuan Li, Zefan Zhang, Bowen Cao, Wai Lam

D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)

Challenge:	Textual frequency is a topic of understudied research, but its relevance to Large Language Models is not well understood.
Approach:	They propose a framework to estimate textual data frequency using a paraphraser and a textual distillation method to refine LLMs.
Outcome:	The proposed framework can be used to estimate sentence-level frequency with word-level frequencies.

Copied to clipboard

Guangze Gao, Zixuan Li, Chunfeng Yuan, Jiawei Li, Wu Jianzhuo, Yuehao Zhang, Xiaolong Jin, Bing Li, Weiming Hu

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction (2024.findings-acl)

Challenge:	Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator.
Approach:	They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA.
Outcome:	The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ.

Copied to clipboard

Kuan-Hao Huang, I-Hung Hsu, Tanmay Parekh, Zhiyu Xie, Zixuan Zhang, Prem Natarajan, Kai-Wei Chang, Nanyun Peng, Heng Ji

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Challenge:	Recent studies suggest that event extraction evaluations may not accurately reflect the true performance.
Approach:	They propose a standardized, fair, and reproducible benchmark for event extraction . they use standardized scripts and splits for 16 datasets spanning eight domains .
Outcome:	The proposed benchmarks show that they struggle to achieve satisfactory performance.

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Dialogue Systems & Conversational Agents

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)

Copied to clipboard

Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction (2021.naacl-main)

Challenge:	Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters.
Approach:	They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer.
Outcome:	The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA.

Copied to clipboard

Zixuan Zhang, Heng Ji

Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)

Challenge:	Abstract Meaning Representation (IE) and Information Extraction (IE), both focus on extracting the main information from natural language texts.
Approach:	They propose an AMR-guided framework for joint information extraction using a pre-trained AMR parser.
Outcome:	The proposed framework achieves state-of-the-art on all IE subtasks.

Copied to clipboard

Zhuo Chen, Zhao Zhang, Zixuan Li, Fei Wang, Yutao Zeng, Xiaolong Jin, Yongjun Xu

Multimodality

Challenge:	Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively.
Approach:	They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions.
Outcome:	The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions.

Enhancing Multi-Document Summarization with Cross-Document Graph-based Information Extraction (2023.eacl-main)

Copied to clipboard

Zixuan Zhang, Heba Elfardy, Markus Dreyer, Kevin Small, Heng Ji, Mohit Bansal

SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models (2025.emnlp-main)

Challenge:	Information extraction (IE) and summarization (summarization) are closely related, but both aims to abstract the most salient information into a generated text summary.
Approach:	They propose to use structured IE graphs to enhance the abstractive summarization task by using cross-document IE output to incorporate an alignment loss between IE nodes and their text spans to reduce inconsistencies.
Outcome:	The proposed model can generate summaries that are more factual while not losing abstractiveness.

Copied to clipboard

Hongyuan Lu, Zixuan Li, Zefan Zhang, Wai Lam

Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

Challenge:	Existing large language models only support hundreds of languages, and they are usually limited in English.
Approach:	They propose a task to automatically select which dictionary to use to enhance translation . they call it Select Low-frequency Words!, which inherits advantage of dictionary-based methods .
Outcome:	The proposed method can save tokens and improve translation performance on 100 languages.

Copied to clipboard

Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng

Multimodality

Challenge:	Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach:	They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome:	The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs (2025.emnlp-main)

Copied to clipboard

Zixuan Weng, Xiaolong Jin, Jinyuan Jia, Xiangyu Zhang