arXiv subjects

Dongwon Lee

Publications and source records attributed to Dongwon Lee.

At least 55 records · Page 3Linked to original sources

arXiv2025

Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs

The rapid advancement of Large Language Models (LLMs) has enabled the generation of highly realistic synthetic data. We identify a new vulnerability, LLMs generating convincing career trajectories in fake resumes and explore effective detection methods. To address this challenge, we construct a dataset of machine-generated career trajectories using LLMs and various methods, and demonstrate that conventional text-based detectors perform poorly on structured career data. We propose CareerScape, a novel heterogeneous, hierarchical multi-layer graph framework that models career entities and their relations in a unified global graph built from genuine resumes. Unlike conventional classifiers that treat each instance independently, CareerScape employs a structure-aware framework that augments user-specific subgraphs with trusted neighborhood information from a global graph, enabling the model to capture both global structural patterns and local inconsistencies indicative of synthetic career paths. Experimental results show that CareerScape outperforms state-of-the-art baselines by 5.8-85.0% relatively, highlighting the importance of structure-aware detection for machine-generated content.

cs.CR↗

arXiv2025

LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles

Figure captions are crucial for helping readers understand and remember a figure's key message. Many models have been developed to generate these captions, helping authors compose better quality captions more easily. Yet, authors almost always need to revise generic AI-generated captions to match their writing style and the domain's style, highlighting the need for personalization. Despite language models' personalization (LaMP) advances, these technologies often focus on text-only settings and rarely address scenarios where both inputs and profiles are multimodal. This paper introduces LaMP-Cap, a dataset for personalized figure caption generation with multimodal figure profiles. For each target figure, LaMP-Cap provides not only the needed inputs, such as figure images, but also up to three other figures from the same document--each with its image, caption, and figure-mentioning paragraphs--as a profile to characterize the context. Experiments with four LLMs show that using profile information consistently helps generate captions closer to the original author-written ones. Ablation studies reveal that images in the profile are more helpful than figure-mentioning paragraphs, highlighting the advantage of using multimodal profiles over text-only ones.

cs.CL↗

arXiv2025

SUA: Stealthy Multimodal Large Language Model Unlearning Attack

Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are proposed, which fine-tune MLLMs to reduce the ``forget'' sensitive information. However, it remains unclear whether the knowledge has been truly forgotten or just hidden in the model. Therefore, we propose to study a novel problem of LLM unlearning attack, which aims to recover the unlearned knowledge of an unlearned LLM. To achieve the goal, we propose a novel framework Stealthy Unlearning Attack (SUA) framework that learns a universal noise pattern. When applied to input images, this noise can trigger the model to reveal unlearned content. While pixel-level perturbations may be visually subtle, they can be detected in the semantic embedding space, making such attacks vulnerable to potential defenses. To improve stealthiness, we introduce an embedding alignment loss that minimizes the difference between the perturbed and denoised image embeddings, ensuring the attack is semantically unnoticeable. Experimental results show that SUA can effectively recover unlearned information from MLLMs. Furthermore, the learned noise generalizes well: a single perturbation trained on a subset of samples can reveal forgotten content in unseen images. This indicates that knowledge reappearance is not an occasional failure, but a consistent behavior.

cs.LG↗

arXiv2025

Catch Me if You Search: When Contextual Web Search Results Affect the Detection of Hallucinations

While we increasingly rely on large language models (LLMs) for various tasks, these models are known to produce inaccurate content or 'hallucinations' with potentially disastrous consequences. The recent integration of web search results into LLMs prompts the question of whether people utilize them to verify the generated content, thereby accurately detecting hallucinations. An online experiment (N=560) investigated how the provision of search results, either static (i.e., fixed search results provided by LLM) or dynamic (i.e., participant-led searches), affects participants' perceived accuracy of LLM-generated content (i.e., genuine, minor hallucination, major hallucination), self-confidence in accuracy ratings, as well as their overall evaluation of the LLM, as compared to the control condition (i.e., no search results). Results showed that participants in both static and dynamic conditions (vs. control) rated hallucinated content to be less accurate and perceived the LLM more negatively. However, those in the dynamic condition rated genuine content as more accurate and demonstrated greater overall self-confidence in their assessments than those in the static search or control conditions. We highlighted practical implications of incorporating web search functionality into LLMs in real-world contexts.

cs.HC↗

arXiv2025

IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection

Interpreting figurative language such as sarcasm across multi-modal inputs presents unique challenges, often requiring task-specific fine-tuning and extensive reasoning steps. However, current Chain-of-Thought approaches do not efficiently leverage the same cognitive processes that enable humans to identify sarcasm. We present IRONIC, an in-context learning framework that leverages Multi-modal Coherence Relations to analyze referential, analogical and pragmatic image-text linkages. Our experiments show that IRONIC achieves state-of-the-art performance on zero-shot Multi-modal Sarcasm Detection across different baselines. This demonstrates the need for incorporating linguistic and cognitive insights into the design of multi-modal reasoning strategies. Our code is available at: https://github.com/aashish2000/IRONIC

cs.CL↗

arXiv2025

MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking

Despite the growing popularity of audio platforms, fact-checking spoken content remains significantly underdeveloped. Misinformation in speech often unfolds across multi-turn dialogues, shaped by speaker interactions, disfluencies, overlapping speech, and emotional tone-factors that complicate both claim detection and verification. Existing datasets fall short by focusing on isolated sentences or text transcripts, without modeling the conversational and acoustic complexity of spoken misinformation. We introduce MAD (Multi-turn Audio Dialogues), the first fact-checking dataset aligned with multi-turn spoken dialogues and corresponding audio. MAD captures how misinformation is introduced, contested, and reinforced through natural conversation. Each dialogue includes annotations for speaker turns, dialogue scenarios, information spread styles, sentence-level check-worthiness, and both sentence- and dialogue-level veracity. The dataset supports two core tasks: check-worthy claim detection and claim verification. Benchmarking shows that even strong pretrained models reach only 72-74% accuracy at the sentence level and 71-72% at the dialogue level in claim verification, underscoring MAD's difficulty. MAD offers a high-quality benchmark for advancing multimodal and conversational fact-checking, while also surfacing open challenges related to reasoning over speech and dialogue dynamics.

cs.SI↗

arXiv2025

A New Lens on Homelessness: Daily Tent Monitoring with 311 Calls and Street Images

Homelessness in the United States has surged to levels unseen since the Great Depression. However, existing methods for monitoring it, such as point-in-time (PIT) counts, have limitations in terms of frequency, consistency, and spatial detail. This study proposes a new approach using publicly available, crowdsourced data, specifically 311 Service Calls and street-level imagery, to track and forecast homeless tent trends in San Francisco. Our predictive model captures fine-grained daily and neighborhood-level variations, uncovering patterns that traditional counts often overlook, such as rapid fluctuations during the COVID-19 pandemic and spatial shifts in tent locations over time. By providing more timely, localized, and cost-effective information, this approach serves as a valuable tool for guiding policy responses and evaluating interventions aimed at reducing unsheltered homelessness.

cs.LG↗

arXiv2025

From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models

With the rapid growth of Large Language Models (LLMs), safeguarding textual content against unauthorized use is crucial. Watermarking offers a vital solution, protecting both - LLM-generated and plain text sources. This paper presents a unified overview of different perspectives behind designing watermarking techniques through a comprehensive survey of the research literature. Our work has two key advantages: (1) We analyze research based on the specific intentions behind different watermarking techniques, evaluation datasets used, and watermarking addition and removal methods to construct a cohesive taxonomy. (2) We highlight the gaps and open challenges in text watermarking to promote research protecting text authorship. This extensive coverage and detailed analysis sets our work apart, outlining the evolving landscape of text watermarking in Language Models.

cs.CL↗

arXiv2025

CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?

Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical correctness in downstream tasks, with limited emphasis on evaluating MLLMs' ability to interpret pragmatic cues and intermodal relationships. To address this gap, we assess the competency of MLLMs in performing Multimodal Discourse Analysis (MDA) using Coherence Relations. Our benchmark, CORDIAL, encompasses a broad spectrum of Coherence Relations across 3 different discourse domains at varying levels of granularity. Through our experiments on 10+ MLLMs employing different prompting strategies, we show that even top models like Gemini 1.5 Pro and GPT-4o fail to match the performance of simple classifier-based baselines. This study emphasizes the need to move beyond similarity-based metrics and adopt a discourse-driven framework for evaluating MLLMs, providing a more nuanced assessment of their capabilities. The benchmark and code are available at: https://aashish2000.github.io/CORDIAL/

cs.CL↗

arXiv2025

RONA: Pragmatically Diverse Image Captioning with Coherence Relations

Writing Assistants (e.g., Grammarly, Microsoft Copilot) traditionally generate diverse image captions by employing syntactic and semantic variations to describe image components. However, human-written captions prioritize conveying a central message alongside visual descriptions using pragmatic cues. To enhance caption diversity, it is essential to explore alternative ways of communicating these messages in conjunction with visual content. We propose RONA, a novel prompting strategy for Multi-modal Large Language Models (MLLM) that leverages Coherence Relations as a controllable axis for pragmatic variations. We demonstrate that RONA generates captions with better overall diversity and ground-truth alignment, compared to MLLM baselines across multiple domains. Our code is available at: https://github.com/aashish2000/RONA

cs.CL↗

arXiv2025

Partisan Fact-Checkers' Warnings Can Effectively Correct Individuals' Misbeliefs About Political Misinformation

Political misinformation, particularly harmful when it aligns with individuals' preexisting beliefs and political ideologies, has become widespread on social media platforms. In response, platforms like Facebook and X introduced warning messages leveraging fact-checking results from third-party fact-checkers to alert users against false content. However, concerns persist about the effectiveness of these fact-checks, especially when fact-checkers are perceived as politically biased. To address these concerns, this study presents findings from an online human-subject experiment (N=216) investigating how the political stances of fact-checkers influence their effectiveness in correcting misbeliefs about political misinformation. Our findings demonstrate that partisan fact-checkers can decrease the perceived accuracy of political misinformation and correct misbeliefs without triggering backfire effects. This correction is even more pronounced when the misinformation aligns with individuals' political ideologies. Notably, while previous research suggests that fact-checking warnings are less effective for conservatives than liberals, our results suggest that explicitly labeled partisan fact-checkers, positioned as political counterparts to conservatives, are particularly effective in reducing conservatives' misbeliefs toward pro-liberal misinformation.

cs.HC↗

arXiv2025

NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models

Online texts with toxic content are a clear threat to the users on social media in particular and society in general. Although many platforms have adopted various measures (e.g., machine learning-based hate-speech detection systems) to diminish their effect, toxic content writers have also attempted to evade such measures by using cleverly modified toxic words, so-called human-written text perturbations. Therefore, to help build automatic detection tools to recognize those perturbations, prior methods have developed sophisticated techniques to generate diverse adversarial samples. However, we note that these ``algorithms"-generated perturbations do not necessarily capture all the traits of ``human"-written perturbations. Therefore, in this paper, we introduce a novel, high-quality dataset of human-written perturbations, named as NoisyHate, that was created from real-life perturbations that are both written and verified by human-in-the-loop. We show that perturbations in NoisyHate have different characteristics than prior algorithm-generated toxic datasets show, and thus can be in particular useful to help develop better toxic speech detection solutions. We thoroughly validate NoisyHate against state-of-the-art language models, such as BERT and RoBERTa, and black box APIs, such as Perspective API, on two tasks, such as perturbation normalization and understanding.

cs.LG↗

arXiv2025

Could AI Trace and Explain the Origins of AI-Generated Images and Text?

AI-generated content is becoming increasingly prevalent in the real world, leading to serious ethical and societal concerns. For instance, adversaries might exploit large multimodal models (LMMs) to create images that violate ethical or legal standards, while paper reviewers may misuse large language models (LLMs) to generate reviews without genuine intellectual effort. While prior work has explored detecting AI-generated images and texts, and occasionally tracing their source models, there is a lack of a systematic and fine-grained comparative study. Important dimensions--such as AI-generated images vs. text, fully vs. partially AI-generated images, and general vs. malicious use cases--remain underexplored. Furthermore, whether AI systems like GPT-4o can explain why certain forged content is attributed to specific generative models is still an open question, with no existing benchmark addressing this. To fill this gap, we introduce AI-FAKER, a comprehensive multimodal dataset with over 280,000 samples spanning multiple LLMs and LMMs, covering both general and malicious use cases for AI-generated images and texts. Our experiments reveal two key findings: (i) AI authorship detection depends not only on the generated output but also on the model's original training intent; and (ii) GPT-4o provides highly consistent but less specific explanations when analyzing content produced by OpenAI's own models, such as DALL-E and GPT-4o itself.

cs.CL↗

arXiv2025

Generative AI Policies under the Microscope: How CS Conferences Are Navigating the New Frontier in Scholarly Writing

As the use of Generative AI (Gen-AI) in scholarly writing and peer reviews continues to rise, it is essential for the computing field to establish and adopt clear Gen-AI policies. This study examines the landscape of Gen-AI policies across 64 major Computer Science conferences and offers recommendations for promoting more effective and responsible use of Gen-AI in the field.

cs.CY↗

arXiv2025

Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?

Recent studies show LLMs struggle with complex instructions involving multiple constraints (e.g., length, format, sentiment). Existing works address this issue by fine-tuning, which heavily relies on fine-tuning data quality and is computational expensive. An alternative is leveraging LLMs' self-correction to refine responses for better constraint adherence. However, this is limited by the feedback quality, as LLMs cannot generate reliable feedback or detect errors. Moreover, its effectiveness relies on few-shot examples illustrating response modifications. As constraints in complex instructions are diverse, manually crafting such examples for each constraint type can be labor-intensive and sub-optimal. To address these two challenges, we propose the Divide-Verify-Refine (DVR) framework with three steps: (1) Divide complex instructions into single constraints and prepare appropriate tools; (2) Verify responses using tools that provide rigorous check and textual guidance (e.g., Python toolkit for format checks or pre-trained classifiers for content analysis); (3) Refine: To maximize refinement effectiveness, we propose dynamic few-shot prompting, where a refinement repository collects successful refinements, and these examples are selectively retrieved for future refinements. Recognizing the lack of complexity in existing datasets, we create a new dataset of complex instructions. DVR doubles Llama3.1-8B's constraint adherence and triples Mistral-7B's performance.

cs.AI↗

arXiv2025

PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection

Recent studies have raised concerns about the potential threats large language models (LLMs) pose to academic integrity and copyright protection. Yet, their investigation is predominantly focused on literal copies of original texts. Also, how LLMs can facilitate the detection of LLM-generated plagiarism remains largely unexplored. To address these gaps, we introduce \textbf{\sf PlagBench}, a dataset of 46.5K synthetic text pairs that represent three major types of plagiarism: verbatim copying, paraphrasing, and summarization. These samples are generated by three advanced LLMs. We rigorously validate the quality of PlagBench through a combination of fine-grained automatic evaluation and human annotation. We then utilize this dataset for two purposes: (1) to examine LLMs' ability to transform original content into accurate paraphrases and summaries, and (2) to evaluate the plagiarism detection performance of five modern LLMs alongside three specialized plagiarism checkers. Our results show that GPT-3.5 Turbo can produce high-quality paraphrases and summaries without significantly increasing text complexity compared to GPT-4 Turbo. However, in terms of detection, GPT-4 outperforms other LLMs and commercial detection tools by 20%, highlights the evolving capabilities of LLMs not only in content generation but also in plagiarism detection. Data and source code are available at https://github.com/Brit7777/plagbench.

cs.CL↗

arXiv2025

CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysis

The rise of unifying frameworks that enable seamless interoperability of Large Language Models (LLMs) has made LLM-LLM collaboration for open-ended tasks a possibility. Despite this, there have not been efforts to explore such collaborative writing. We take the next step beyond human-LLM collaboration to explore this multi-LLM scenario by generating the first exclusively LLM-generated collaborative stories dataset called CollabStory. We focus on single-author to multi-author (up to 5 LLMs) scenarios, where multiple LLMs co-author stories. We generate over 32k stories using open-source instruction-tuned LLMs. Further, we take inspiration from the PAN tasks that have set the standard for human-human multi-author writing tasks and analysis. We extend their authorship-related tasks for multi-LLM settings and present baselines for LLM-LLM collaboration. We find that current baselines are not able to handle this emerging scenario. Thus, CollabStory is a resource that could help propel an understanding as well as the development of new techniques to discern the use of multiple LLMs. This is crucial to study in the context of writing tasks since LLM-LLM collaboration could potentially overwhelm ongoing challenges related to plagiarism detection, credit assignment, maintaining academic integrity in educational settings, and addressing copyright infringement concerns. We make our dataset and code available at https://github.com/saranya-venkatraman/CollabStory.

cs.CL↗

arXiv2025

CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking

Fact-checking the truthfulness of claims usually requires reasoning over multiple evidence sentences. Oftentimes, evidence sentences may not be always self-contained, and may require additional contexts and references from elsewhere to understand coreferential expressions, acronyms, and the scope of a reported finding. For example, evidence sentences from an academic paper may need contextual sentences in the paper and descriptions in its cited papers to determine the scope of a research discovery. However, most fact-checking models mainly focus on the reasoning within evidence sentences, and ignore the auxiliary contexts and references. To address this problem, we propose a novel method, Context- and Reference-augmented Reasoning and Prompting. For evidence reasoning, we construct a three-layer evidence graph with evidence, context, and reference layers. We design intra- and cross-layer reasoning to integrate three graph layers into a unified evidence embedding. For verdict prediction, we design evidence-conditioned prompt encoder, which produces unique prompt embeddings for each claim. These evidence-conditioned prompt embeddings and claims are unified for fact-checking. Experiments verify the strength of our model.

cs.CL↗