arXiv subjects

Haopeng Zhang

Publications and source records attributed to Haopeng Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

MPCI-Bench: A Benchmark for Multimodal Pairwise Contextual Integrity Evaluation of Language Model Agents

As language-model agents evolve from passive chatbots into proactive assistants that handle personal data, evaluating their adherence to social norms becomes increasingly critical, often through the lens of Contextual Integrity (CI). However, existing CI benchmarks are largely text-centric and primarily emphasize negative refusal scenarios, overlooking multimodal privacy risks and the fundamental trade-off between privacy and utility. In this paper, we introduce MPCI-Bench, the first Multimodal Pairwise Contextual Integrity benchmark for evaluating privacy behavior in agentic settings. MPCI-Bench consists of paired positive and negative instances derived from the same visual source and instantiated across three tiers: normative Seed judgments, context-rich Story reasoning, and executable agent action Traces. Data quality is ensured through a Tri-Principle Iterative Refinement pipeline. Evaluations of state-of-the-art multimodal models reveal systematic failures to balance privacy and utility and a pronounced modality leakage gap, where sensitive visual information is leaked more frequently than textual information. We will open-source MPCI-Bench to facilitate future research on agentic CI.

cs.AI↗

arXiv2026

StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs

Large language models (LLMs) have shown strong performance in zero-shot summarization, but often struggle to model document structure and identify salient information in long texts. In this work, we introduce StrucSum, a training-free prompting framework that enhances LLM reasoning through sentence-level graph structures. StrucSum injects structural signals into prompts via three targeted strategies: Neighbor-Aware Prompting (NAP) for local context, Centrality-Aware Prompting (CAP) for importance estimation, and Centrality-Guided Masking (CGM) for efficient input reduction. Experiments on ArXiv, PubMed, and Multi-News demonstrate that StrucSum consistently improves both summary quality and factual consistency over unsupervised baselines and vanilla prompting. In particular, on ArXiv, it increases FactCC and SummaC by 19.2\% and 8.0\% points, demonstrating stronger alignment between summaries and source content. The ablation study shows that the combination of multiple strategies does not yield clear performance gains; therefore, structure-aware prompting with graph-based information represents a promising and underexplored direction for the advancement of zero-shot extractive summarization with LLMs. Our source code is publicly available.

cs.CL↗

arXiv2026

MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding

Long videos, ranging from minutes to hours, present significant challenges for current Multi-modal Large Language Models (MLLMs) due to their complex events, diverse scenes, and long-range dependencies. Direct encoding of such videos is computationally too expensive, while simple video-to-text conversion often results in redundant or fragmented content. To address these limitations, we introduce MMViR, a novel multi-modal, multi-grained structured representation for long video understanding. MMViR identifies key turning points to segment the video and constructs a three-level description that couples global narratives with fine-grained visual details. This design supports efficient query-based retrieval and generalizes well across various scenarios. Extensive evaluations across three tasks, including QA, summarization, and retrieval, show that MMViR outperforms the prior strongest method, achieving a 19.67% improvement in hour-long video understanding while reducing processing latency to 45.4% of the original.

cs.CV↗

arXiv2025

Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation

While large language models (LLMs) have achieved remarkable success in providing trustworthy responses for knowledge-intensive tasks, they still face critical limitations such as hallucinations and outdated knowledge. To address these issues, the retrieval-augmented generation (RAG) framework enhances LLMs with access to external knowledge via a retriever, enabling more accurate and real-time outputs about the latest events. However, this integration brings new security vulnerabilities: the risk that malicious content in the external database can be retrieved and used to manipulate model outputs. Although prior work has explored attacks on RAG systems, existing approaches either rely heavily on access to the retriever or fail to jointly consider both retrieval and generation stages, limiting their effectiveness, particularly in black-box scenarios. To overcome these limitations, we propose Token-level Precise Attack on the RAG (TPARAG), a novel framework that targets both white-box and black-box RAG systems. TPARAG leverages a lightweight white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level, ensuring both retrievability and high attack success in generation. Extensive experiments on open-domain QA datasets demonstrate that TPARAG consistently outperforms previous approaches in retrieval-stage and end-to-end attack effectiveness. These results further reveal critical vulnerabilities in RAG pipelines and offer new insights into improving their robustness.

cs.CL↗

arXiv2025

FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models

While large language models (LLMs) have demonstrated impressive performance across a wide range of natural language processing (NLP) tasks in high-resource languages, their capabilities in low-resource and minority languages remain significantly underexplored. Formosan languages -- a subgroup of Austronesian languages spoken in Taiwan -- are both linguistically rich and endangered, largely due to the sociolinguistic dominance of Mandarin. In this work, we introduce FORMOSANBENCH, the first benchmark for evaluating LLMs on low-resource Austronesian languages. It covers three endangered Formosan languages: Atayal, Amis, and Paiwan, across three core NLP tasks: machine translation, automatic speech recognition (ASR), and text summarization. We assess model performance in zero-shot, 10-shot, and fine-tuned settings using FORMOSANBENCH. Our results reveal a substantial performance gap between high-resource and Formosan languages. Existing LLMs consistently underperform across all tasks, with 10-shot learning and fine-tuning offering only limited improvements. These findings underscore the urgent need for more inclusive NLP technologies that can effectively support endangered and underrepresented languages. We release our datasets and code to facilitate future research in this direction.

cs.CL↗

arXiv2025

MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming

Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space through safety-constrained graph evolution. At its core, MermaidFlow represent workflows as a verifiable intermediate representation using Mermaid, a structured and human-interpretable graph language. We formulate domain-aware evolutionary operators, i.e., crossover, mutation, insertion, and deletion, to preserve semantic correctness while promoting structural diversity, enabling efficient exploration of a high-quality, statically verifiable workflow space. Without modifying task settings or evaluation protocols, MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark. The experimental results demonstrate that safety-constrained graph evolution offers a scalable, modular foundation for robust and interpretable agentic reasoning systems.

cs.LG↗

arXiv2025

A Structure-aware Generative Model for Biomedical Event Extraction

Biomedical Event Extraction (BEE) is a challenging task that involves modeling complex relationships between fine-grained entities in biomedical text. BEE has traditionally been formulated as a classification problem. With recent advancements in large language models (LLMs), generation-based models that cast event extraction as a sequence generation problem have attracted attention in the NLP research community. However, current generative models often overlook cross-instance information in complex event structures, such as nested and overlapping events, which constitute over 20% of events in benchmark datasets. In this paper, we propose GenBEE, an event structure-aware generative model that captures complex event structures in biomedical text for biomedical event extraction. GenBEE constructs event prompts that distill knowledge from LLMs to incorporate both label semantics and argument dependency relationships. In addition, GenBEE generates prefixes with event structural prompts to incorporate structural features to improve the model's overall performance. We have evaluated the proposed GenBEE model on three widely used BEE benchmark datasets, namely MLEE, GE11, and PHEE. Experimental results show that GenBEE has achieved state-of-the-art performance on the MLEE and GE11 datasets, and achieved competitive results when compared to the state-of-the-art classification-based models on the PHEE dataset.

cs.CL↗

arXiv2025

Wi-Chat: Large Language Model Powered Wi-Fi Sensing

Recent advancements in Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, their potential to integrate physical model knowledge for real-world signal interpretation remains largely unexplored. In this work, we introduce Wi-Chat, the first LLM-powered Wi-Fi-based human activity recognition system. We demonstrate that LLMs can process raw Wi-Fi signals and infer human activities by incorporating Wi-Fi sensing principles into prompts. Our approach leverages physical model insights to guide LLMs in interpreting Channel State Information (CSI) data without traditional signal processing techniques. Through experiments on real-world Wi-Fi datasets, we show that LLMs exhibit strong reasoning capabilities, achieving zero-shot activity recognition. These findings highlight a new paradigm for Wi-Fi sensing, expanding LLM applications beyond conventional language tasks and enhancing the accessibility of wireless sensing for real-world deployments.

cs.CL↗

arXiv2024

DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization

Most research on abstractive summarization focuses on single-domain applications, often neglecting how domain shifts between documents affect performance and the generalization ability of summarization models. To address this issue, we introduce DomainSum, a hierarchical benchmark designed to capture fine-grained domain shifts in abstractive summarization. We categorize these shifts into three levels: genre, style, and topic, and demonstrate through comprehensive benchmark analysis that they follow a hierarchical structure. Furthermore, we evaluate the domain generalization capabilities of commonly used pre-trained language models (PLMs) and large language models (LLMs) in in-domain and cross-domain settings.

cs.CL↗

arXiv2024

Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval

Recent research has explored distilling knowledge from large language models (LLMs) to optimize retriever models, especially within the retrieval-augmented generation (RAG) framework. However, most existing training methods rely on extracting supervision signals from LLMs' weights or their output probabilities, which is not only resource-intensive but also incompatible with black-box LLMs. In this paper, we introduce \textit{Intermediate Distillation}, a data-efficient knowledge distillation training scheme that treats LLMs as black boxes and distills their knowledge via an innovative LLM-ranker-retriever pipeline, solely using LLMs' ranking generation as the supervision signal. Extensive experiments demonstrate that our proposed method can significantly improve the performance of retriever models with only 1,000 training instances. Moreover, our distilled retriever model significantly boosts performance in question-answering tasks within the RAG framework, demonstrating the potential of LLMs to economically and effectively train smaller models.

cs.IR↗

arXiv2024

A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models

Text summarization research has undergone several significant transformations with the advent of deep neural networks, pre-trained language models (PLMs), and recent large language models (LLMs). This survey thus provides a comprehensive review of the research progress and evolution in text summarization through the lens of these paradigm shifts. It is organized into two main parts: (1) a detailed overview of datasets, evaluation metrics, and summarization methods before the LLM era, encompassing traditional statistical methods, deep learning approaches, and PLM fine-tuning techniques, and (2) the first detailed examination of recent advancements in benchmarking, modeling, and evaluating summarization in the LLM era. By synthesizing existing literature and presenting a cohesive overview, this survey also discusses research trends, open challenges, and proposes promising research directions in summarization, aiming to guide researchers through the evolving landscape of summarization research.

cs.CL↗

arXiv2024

MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/.

cs.CV↗

arXiv2024

XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates

Text editing is a crucial task of modifying text to better align with user intents. However, existing text editing benchmark datasets contain only coarse-grained instructions and lack explainability, thus resulting in outputs that deviate from the intended changes outlined in the gold reference. To comprehensively investigate the text editing capabilities of large language models (LLMs), this paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing. XATU considers finer-grained text editing tasks of varying difficulty (simplification, grammar check, fact-check, etc.), incorporating lexical, syntactic, semantic, and knowledge-intensive edit aspects. To enhance interpretability, we combine LLM-based annotation and human annotation, resulting in a benchmark that includes fine-grained instructions and gold-standard edit explanations. By evaluating existing LLMs against our benchmark, we demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks. Furthermore, extensive experimentation reveals the significant role of explanations in fine-tuning language models for text editing tasks. The benchmark will be open-sourced to support reproduction and facilitate future research at~\url{https://github.com/megagonlabs/xatu}.

cs.CL↗

arXiv2024

Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is attention distillation, which uses attention scores as a supervision signal instead of manually annotated query-document pairs. Despite its growing popularity, the detailed mechanisms behind the success of attention distillation remain unexplored, particularly the specific patterns it leverages to benefit training. In this paper, we address this gap by conducting a comprehensive review of attention distillation workflow and identifying key factors influencing the learning quality of retrieval-augmented language models. We further propose indicators for optimizing models' training methods and avoiding ineffective training.

cs.CL↗

arXiv2023

A Revisit of Fake News Dataset with Augmented Fact-checking by ChatGPT

The proliferation of fake news has emerged as a critical issue in recent years, requiring significant efforts to detect it. However, the existing fake news detection datasets are sourced from human journalists, which are likely to have inherent bias limitations due to the highly subjective nature of this task. In this paper, we revisit the existing fake news dataset verified by human journalists with augmented fact-checking by large language models (ChatGPT), and we name the augmented fake news dataset ChatGPT-FC. We quantitatively analyze the distinctions and resemblances between human journalists and LLM in assessing news subject credibility, news creator credibility, time-sensitive, and political framing. Our findings highlight LLM's potential to serve as a preliminary screening method, offering a promising avenue to mitigate the inherent biases of human journalists and enhance fake news detection.

cs.CL↗

arXiv2023

Extractive Summarization via ChatGPT for Faithful Summary Generation

Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent introduction of large language models has attracted significant interest in the NLP community due to its remarkable performance on a wide range of downstream tasks. This paper first presents a thorough evaluation of ChatGPT's performance on extractive summarization and compares it with traditional fine-tuning methods on various benchmark datasets. Our experimental analysis reveals that ChatGPT exhibits inferior extractive summarization performance in terms of ROUGE scores compared to existing supervised systems, while achieving higher performance based on LLM-based evaluation metrics. In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance. Furthermore, we find that applying an extract-then-generate pipeline with ChatGPT yields significant performance improvements over abstractive baselines in terms of summary faithfulness. These observations highlight potential directions for enhancing ChatGPT's capabilities in faithful summarization using two-stage approaches.

cs.CL↗

arXiv2023

SummIt: Iterative Text Summarization via ChatGPT

Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step. However, the one-shot summarization setting is sometimes inadequate, as the generated summary may contain hallucinations or overlook essential details related to the reader's interests. This paper addresses this limitation by proposing SummIt, an iterative text summarization framework based on large language models like ChatGPT. Our framework enables the model to refine the generated summary iteratively through self-evaluation and feedback, resembling humans' iterative process when drafting and revising summaries. Furthermore, we explore the potential benefits of integrating knowledge and topic extractors into the framework to enhance summary faithfulness and controllability. We automatically evaluate the performance of our framework on three benchmark summarization datasets. We also conduct a human evaluation to validate the effectiveness of the iterative refinements and identify a potential issue of over-correction.

cs.CL↗

arXiv2023

Convolution and Attention Mixer for Synthetic Aperture Radar Image Change Detection

Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural networks (CNNs), with limited consideration of global attention mechanism. In this letter, we explore Transformer-like architecture for SAR change detection to incorporate global attention. To this end, we propose a convolution and attention mixer (CAMixer). First, to compensate the inductive bias for Transformer, we combine self-attention with shift convolution in a parallel way. The parallel design effectively captures the global semantic information via the self-attention and performs local feature extraction through shift convolution simultaneously. Second, we adopt a gating mechanism in the feed-forward network to enhance the non-linear feature transformation. The gating mechanism is formulated as the element-wise multiplication of two parallel linear layers. Important features can be highlighted, leading to high-quality representations against speckle noise. Extensive experiments conducted on three SAR datasets verify the superior performance of the proposed CAMixer. The source codes will be publicly available at https://github.com/summitgao/CAMixer .

eess.IV↗