Papers by Xinyue Zhang
Temporal Knowledge Graph Reasoning with Dynamic Hypergraph Embedding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that model temporal dynamics with knowledge graphs and graph convolution networks lack high-order interactions between objects in TKG, which is an important factor to predict future facts. |
| Approach: | They propose to embed temporal knowledge graph reasoning by constructing hypergraphs based on temporal information graphs at different timestamps and then adapt dynamic meta-embedding to fit TKG. |
| Outcome: | The proposed method outperforms baseline models on public TKG datasets and provides good interpretation for the predicted results. |
GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been widely deployed as autonomous agents capable of following user instructions and making decisions in real-world applications. |
| Approach: | They propose a benchmark to evaluate LLMs' ability to follow domain-oriented guidelines . they evaluate Lms on three critical aspects: adherence to diverse rules, robustness to rule updates . |
| Outcome: | The proposed benchmark evaluates LLMs on three critical aspects: adherence to diverse rules, robustness to rule updates, and alignment with human preferences. |
What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAE (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches ignore the overlap knowledge across datasets, preventing models from achieving better performance. |
| Approach: | They propose to divide the EAE knowledge into overlap knowledge across datasets and specific knowledge of the target dataset. |
| Outcome: | The proposed model outperforms the baseline model with a large margin when only ten records are available in the target dataset. |
Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit notable deficiencies in temporal reasoning . phrasing changes can lead LLMs to produce inconsistent outputs . |
| Approach: | They investigate the mechanistic interpretability of temporal ordering within event temporal reasoning . they identify a sparse subset of attention heads that are causally responsible for reasoning outcomes . |
| Outcome: | The proposed model outperforms other models in a variety of tasks and is validated by intervention-based experiments. |
The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has shown that high-quality prompts are essential for LLMs to produce accurate and relevant responses. |
| Approach: | They analyze 10,538 in-the-wild prompts collected from various platforms and develop a framework that decomposes the prompts into eight key components. |
| Outcome: | The proposed framework decomposes 10,538 in-the-wild prompts into eight components. |
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to adapt Large Language Models (LLMs) for recommendation encounter significant challenges such as amplification bias and homogeneity. |
| Approach: | They propose a new decoding approach called Debiasing-Diversifying Decoding (D3) that disables length normalization for ghost tokens to alleviate amplification bias and incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity. |
| Outcome: | Extensive experiments on real-world datasets demonstrate the proposed approach’s effectiveness in enhancing accuracy and diversity. |
JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used to mitigate misuse and to align with human values. |
| Approach: | They propose to use large-scale evaluations of various jailbreak attacks to identify key patterns and test them under eight advanced defenses. |
| Outcome: | The proposed attacks achieve high success rates but are easy to mitigate by defenses. |
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated excellent performance in numerous tasks but the parameterized knowledge stored within LLMs may be incomplete and hard to incorporate up-to-date knowledge. |
| Approach: | They propose a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model’s problem-solving capabilities. |
| Outcome: | The proposed method outperforms existing benchmarks on GPT3.5, Llama2 and other large language models significantly enhancing factual reasoning capabilities and reducing hallucinations. |
Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media (2025.acl-long)
Copied to clipboard
| Challenge: | Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs) however, the misuse of AIGTs could have profound implications for public opinion . |
| Approach: | They collect a dataset with 2.4M posts from 3 major social media platforms . they then construct a diverse dataset to train and evaluate AIGT detectors . |
| Outcome: | The proposed dataset analyzes 2.4M posts from 3 major social media platforms from 2022 to 2024 . it finds that Medium and Quora show marked increases in AAR . |
Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs (2025.coling-main)
Copied to clipboard
| Challenge: | Temporal knowledge graph reasoning is a useful tool for many practical tasks. |
| Approach: | They propose a Hawkes process-based Evolutional Representation Learning Network model which learns structural information and evolutional patterns of a TKG simultaneously. |
| Outcome: | The proposed model learns structural information and evolutional patterns of a TKG simultaneously, considering the characteristics of real-world networks: community structure, scale-free and temporal decaying. |
Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer (2026.findings-eacl)
Copied to clipboard
Jinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya, Xinyue Ye, Dongjie Wang, Yanjie Fu, Kunpeng Liu
| Challenge: | Existing studies show that large language models have strong reasoning capabilities through chain-structured methods. |
| Approach: | They propose a framework for navigating and expanding thought structures to overcome blind spots in LLM reasoning. |
| Outcome: | The proposed framework overcomes blind spots in large language models by expanding thought structures . the proposed framework improves accuracy of the final answer and intermediate reasoning steps . |
PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work lacks mitigation strategies against resource consumption attacks . existing work does not provide mitigation strategies for real-world LLM deployments . |
| Approach: | They propose a pluggable and dynamic doS-Defense framework which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides. |
| Outcome: | The proposed framework significantly mitigates resource consumption attacks, improving users’ access capacity by up to 500% during adversarial load. |
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)
Copied to clipboard
Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang
| Challenge: | Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios. |
| Approach: | They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts. |
| Outcome: | The proposed model performs comparable to state-of-the-art large models on the test set. |
Constructing Your Model’s Value Distinction: Towards LLM Alignment with Anchor Words Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a study of large language models (LLMs) shows that they can generate outputs that are honest, positive, harmless, etc. |
| Approach: | They propose a method that amplifies logits difference between positive and negative tokens . they propose to use the logits gap to generate positive and positive tokens after alignment . |
| Outcome: | The proposed method achieves effective alignment, but requires fewer computational resources compared to training-time alignment methods. |
RENN: A Rule Embedding Enhanced Neural Network Framework for Temporal Knowledge Graph Completion (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge graph embedding do not account for structural dependencies between relations. |
| Approach: | They propose a framework that enhances temporal knowledge graph completion through rule embedding. |
| Outcome: | The proposed framework improves temporal knowledge graph completion through rule embedding. |
ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large vision-language models have been widely used but stereotypical biases are unexplored. |
| Approach: | They propose a framework to SCAN stereotypical bias within large vision-language models . they examine stereotype biases with respect to gender and race in three scenarios . |
| Outcome: | The proposed framework can reduce stereotypical biases in large vision-language models . the currently popular models show significant stereotype biase . |
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)
Copied to clipboard
Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang
| Challenge: | Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important . |
| Approach: | They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment . |
| Outcome: | The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility . |
How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study (2026.acl-long)
Copied to clipboard
Zhen Yang, Ping Jian, Zhongbin Guo, Zuming Zhang, Chengzhi Li, Yonghong Deng, Xinyue Zhang, Wenpeng Lu
| Challenge: | Existing studies on spatial intelligence from the perspective of visual-spatial intelligence have not explored whether visual intelligence alone is sufficient to endow models with spatial intelligence. |
| Approach: | They propose to use a linguistic perspective to investigate spatial intelligence from a theoretical perspective. |
| Outcome: | The proposed model performs poorly on the proposed dataset while human can easily achieve 100% accuracy. |
Where CoT Reasoning Commits: Entropy Traces Identify Interpretable Attention Heads (2026.findings-acl)
Copied to clipboard
| Challenge: | a growing body of work suggests a disconnect between the generated rationale and the model's actual choice. |
| Approach: | They propose a mechanism-aware framework that interprets the evolving "choice state" of attention heads during CoT generation . they identify a set of intervention targets and perform Selective Head Fine-Tuning . |
| Outcome: | The proposed framework interprets the "choice state" of attention heads during CoT generation . it detects two functional behaviors: Steadfast Heads and Wavering Heads . |
Unveiling Opinion Evolution via Prompting and Diffusion for Short Video Fake News Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for short video fake news detection ignore the implicit opinions and evolving nature of opinions across modalities. |
| Approach: | They propose a short video fake news model that mines implicit opinions within short videos and promotes the evolution of both explicit and implicit opinions across all modalities. |
| Outcome: | The proposed model outperforms existing methods on a publicly available dataset for short video fake news detection. |
Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful at question-answering but prone to hallucinations due to limited domain-specific or up-to-date knowledge. |
| Approach: | They propose a framework for IDentifying RAG properties in LLM services that integrates LLMs with retrieval systems and adds an external retriever and knowledge database to mitigate hallucinations. |
| Outcome: | The proposed framework detects RAG-enhanced LLMs with 99.97% accuracy with partial or no optional knowledge and nearly 100% when the LLM and database are known. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
ToolGate: Contract-Grounded and Verified Tool Execution for LLMs (2026.findings-acl)
Copied to clipboard
Yanming Liu, Xinyue Peng, Jiannan Cao, Xinyi Wang, Songhang Deng, Jintao Chen, Jianwei Yin, Xuhong Zhang
| Challenge: | Existing frameworks for tool-augmented LLMs rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be trusted. |
| Approach: | They propose a forward execution framework that provides logical safety guarantees and verifiable state evolution for LLM tool calling. |
| Outcome: | The proposed framework improves the reliability and verifiability of tool-augmented LLM systems while maintaining competitive performance on multi-step reasoning tasks. |
Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models for industrial sales require balancing long-term commercial objectives with immediate linguistic constraints such as fluency and compliance. |
| Approach: | They propose a framework that disentangles optimization across time scales by normalizing advantages from turn-level and session-level rewards before fusion. |
| Outcome: | The proposed framework outperforms the state-of-the-art GRPO model in conversion rate and identity detection rate. |
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable in-context learning capabilities in various natural language processing tasks. |
| Approach: | They propose a novel approach ERA-CoT which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chain-of-Thoughts (CoT). |
| Outcome: | The proposed method improves on GPT3.5 and previous SOTA prompting methods by an average of 5.1% compared to previous prompting approaches. |
Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions (2026.findings-acl)
Copied to clipboard
Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian
| Challenge: | Existing advances in Spatial Intelligence rely on vision-Language Models . however, a critical question remains: does spatial understanding originate from visual encoders? |
| Approach: | They propose to evaluate the SI performance of Large Language Models without pixel-level input. |
| Outcome: | The proposed benchmark challenges large language models to perform symbolic reasoning rather than visual pattern matching. |
When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that adversarial prompts can induce GPTs to leak knowledge file content. |
| Approach: | They propose a workflow inspired by Data Security Posture Management to identify five leakage vectors for knowledge file leakage using 651,022 GPT metadata and 11,820 flows. |
| Outcome: | The proposed workflow analyzes 651,022 GPT metadata, 11,820 flows, and 1,466 responses to identify five leakage vectors: metadata, GPT initialization, retrieval, sandboxed execution environments, and prompts. |
Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts to improve task accuracy or enrich COT generation are lacking in multimodal large language models. |
| Approach: | They propose a Faithful-First Reasoning, Planning, and Acting framework that evaluates faithfulness of intermediate reasoning and uses it to plan and execute faithfulness-aware actions during inference. |
| Outcome: | The proposed framework improves perceptual faithfulness by up to 24% over prompt-based and tool-augmented reasoning frameworks without degrading task accuracy. |
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on white-box attacks focus on black-box LLMs, leaving black- box scenarios underexplored. |
| Approach: | They propose an automated algorithm designed for black-box LLMs that constructs the DoS Attack Tree and expands the node coverage to achieve effectiveness under black- box conditions. |
| Outcome: | The proposed algorithm can be used to build a DoS Attack Tree and expand the node coverage to achieve effectiveness under black-box conditions. |