arXiv subjects

Lucy Lu Wang

Publications and source records attributed to Lucy Lu Wang.

At least 19 recordsLinked to original sources

arXiv2026

MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation

Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align with human evaluation, especially for complex tasks that involve multiple modalities. We present MMMG, the first benchmark to bring the verifiable-task paradigm to multimodal generation, spanning 4 modality combinations (image, audio, interleaved text and image, interleaved text and audio). As few multimodal outputs can be checked by programs alone, MMMG targets tasks that are either verifiable or near-verifiable: by providing references, and constraining model judges with explicit rubrics. We keep tasks challenging for generation models while enabling reliable automatic evaluation through a combination of models and programs. MMMG encompasses 55 tasks (including 31 newly developed ones), each with a carefully designed evaluation pipeline, and 1288 instructions to systematically assess reasoning, controllability, and other key capabilities of multimodal generation models. Extensive validation demonstrates that MMMG is highly aligned with human judgment, achieving an average agreement of 94.4%. Benchmarking results on 29 models reveal that even though the state-of-the-art model, GPT Image, achieves 70.7% accuracy for image generation, it falls short on interleaved generation. Furthermore, results suggest considerable improvement space in audio generation, highlighting an important future direction.

cs.AI↗

arXiv2026

You're Hired: Strategic Model Selection for LLM Collaboration

While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems remain bottlenecked on pre-defined and hand-crafted model pools. In this work, we investigate the problem of model selection in multi-LLM systems. We propose and systematically evaluate a taxonomy of 9 selection algorithms ranging from diversity of model descriptions, capability-aware behavioral diversity, and LLM-based recruiters. We conduct extensive experiments across two candidate pools of 10 and 32 models, deployed in four model collaboration algorithms, and evaluated across tasks spanning math, coding, QA, and reasoning. Results demonstrate that successful selection algorithms greatly outperform random or heuristics-based teams such as merely selecting the models with top individual performance, by up to 36.1% across settings. Specifically, capability- and training-based selection strategies alleviate selection variance and achieve the best performance, which we recommend to employ before deploying real-world multi-LLM systems. Further analysis reveals that larger candidate pools pose greater challenges to shallow selection heuristics, while algorithms grounded in interacting with candidate models and understanding model capability robustly filter out misaligned, unsafe models, as well as generalizing to novel, out-of-distribution tasks. Together, we establish that principled and informed team selection is critical and present strong model selection algorithms for assembling effective multi-LLM systems.

cs.CL↗

arXiv2026

ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?

Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ignores differences in readers' information needs and comprehension. In health contexts, this limitation is particularly important because misunderstanding scientific information can affect real-world decisions. Large language models (LLMs) offer new opportunities for personalizing PLS, but it remains unclear whether personalization helps, which strategies are most effective, and how to balance personalization with safety. We introduce ReLay, a dataset of 300 participant--PLS pairs from 50 lay participants in both static (expert-written) and interactive (LLM-personalized) settings. ReLay includes user characteristics, health information needs, information-seeking behavior, comprehension outcomes, interaction logs, and quality ratings. We use ReLay to evaluate five LLMs across two personalization methods. Personalization improves comprehension and perceived quality, but it also raises the risk of reinforcing user biases and introducing hallucinations, revealing a trade-off between personalization and safety. These findings highlight the need for personalization methods that are both effective and trustworthy for diverse lay audiences.

cs.CL↗

arXiv2026

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes

Long chain-of-thought (Long CoT) reasoning improves performance on multi-step problems, but it also induces overthinking. This inefficiency is especially problematic in low-data fine-tuning regimes, where real applications adapt reasoning models with limited supervision and cannot rely on large-scale teacher distillation or heavy test-time control. To address this, we propose STOP (Structured On-policy Pruning), an on-policy algorithm for analyzing and pruning long-form reasoning traces. STOP constructs self-distilled traces from the model. Then it maps each trace into a structured reasoning interface through node segmentation, taxonomy annotation, and reasoning-tree construction. On top of this interface, we introduce ECN (Earliest Correct Node), which retains the shortest prefix ending at the earliest node. Experiments on DeepSeek-R1-Distill-Qwen-7B and DeepSeek-R1-Distill-LLaMA-3-8B across GSM8K, Math 500, and AIME 2024 show that STOP reduces generated tokens by 19.4% to 42.4% while largely preserving accuracy in low-data fine-tuning. Beyond efficiency, our analyses show that STOP induces much smaller distributional shift than teacher-guided pruning, improves the structural efficiency of generated reasoning, and reallocates reasoning effort away from redundant verification and backtracking toward more productive exploration.

cs.CL↗

arXiv2026

Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists

Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have traditionally relied on static alternative text to access figures in papers, the rise of artificial intelligence (AI) has made interactive question-answering (QA) a feasible paradigm for visual exploration; yet little is known about how scientists use visual QA in practice or how to improve its accessibility. In this work, we interview five BLV and five sighted scientists across different STEM fields to understand how they use two AI tools, ChatGPT and Gemini, to query multimodal scientific documents. Our findings characterize how scientists review multimodal content, including existing practices (along with accessibility workarounds) for engaging with visuals, and feedback on the suitability of AI-generated responses to multimodal queries. We further find that vague or incomplete image descriptions, as well as incorrect AI outputs more broadly, can cause both BLV and sighted scientists to abandon AI workflows. To support future research, we additionally contribute a dataset of 115 queries and responses from our participants' interactions with the AI tools for papers in their field. We close by discussing implications for AI-powered scientific QA systems, emphasizing considerations for access across abilities and domains.

cs.HC↗

arXiv2026

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable in the available environment. In such cases, a reliable agent should recognize that further interaction is unlikely to help and abstain from additional tool calls. We define Agentic Abstention, the problem of deciding when an agent should stop acting under uncertainty. Unlike standard LLM abstention, which is usually evaluated as a single-turn answer-or-abstain decision, agentic abstention is a sequential decision problem: an agent can answer, abstain, or gather more information at each turn, and the need to abstain may only become clear after interacting with the environment. We study this problem across web shopping, terminal environments, and question answering, evaluating 13 LLM-as-agent systems and 2 agent scaffolds on more than 28,000 tasks. Our results show that the main challenge is not only whether agents can abstain, but also when they abstain. Some agents never abstain when they should, while others do so only after many unnecessary interactions. This gap is especially large on tasks where the instruction appears feasible until the environment reveals otherwise (e.g., no valid result matches the instruction). We further find that model scale, reasoning, and agent scaffolding affect abstention in different ways, where larger or more capable models sometimes perform worse at timely abstention. Finally, we introduce CONVOLVE, a context engineering method for improving agentic abstention that distills full interaction trajectories into reusable stopping rules. On WebShop, CONVOLVE substantially improves timely abstention without updating model parameters, raising Llama-3.3-70B's timely recall rate from 26.7 to 57.4. Our dataset and code are available at https://lhannnn.github.io/agentic-abstention

cs.AI↗

arXiv2026

Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes

Invasive mechanical ventilation is a lifesaving therapy, but timely, safe discontinuation is essential to preventing extubation failure (EF) and related risks to health. We present a novel approach to EF prediction that leverages features classified in free-text respiratory therapy notes using a large language model and logistic regression pipeline. Applied to a patient cohort from University of Washington Medicine, our method identifies clinically meaningful EF-related features that improve EF prediction performance when included alongside structured patient data. We further highlight how differences in target populations in prior EF prediction studies, such as heterogenous inclusion criteria and EF definition, can lead to systematic differences in model performance and hinder generalizability between studies.

cs.CL↗

arXiv2026

Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation

Human evaluation plays a critical role in assessing the quality of generated text. However, the reliability and reproducibility of these evaluations depend on transparent and well-documented protocols -- details that are frequently missing in current practice. In this work, we conduct a large-scale analysis of human evaluation protocols for evaluating long-form generation tasks in *CL conference publications from 2023--2025, including a full manual review of 284 papers and LLM-assisted analysis for another 1.8k+ papers. We define a set of 20 reportable criteria related to reproducibility of human evaluation studies, and apply these criteria to systematically examine reporting norms and practices within the community. We find widespread under-reporting of important aspects of human evaluation study design, leading to ambiguity about what was measured and how, who contributed judgments, and how judgments should be interpreted. Based on these findings, we outline actionable recommendations to support more transparent and reproducible reporting in future research. Our analysis code and annotated dataset can be found at: https://github.com/larchlab/Illusions-of-the-Gold-Standard

cs.CL↗

arXiv2026

ReFinE: Streamlining UI Mockup Iteration with Research Findings

Although HCI research papers offer valuable design insights, designers often struggle to apply them in design workflows due to difficulties in finding relevant literature, understanding technical jargon, the lack of contextualization, and limited actionability. To address these challenges, we present ReFinE, a Figma plugin that supports real-time design iteration by surfacing contextualized insights from research papers. ReFinE identifies and synthesizes design implications from HCI literature relevant to the mockup's design context, and tailors this research evidence to a specific design mockup by providing actionable visual guidance on how to update the mockup. To assess the system's effectiveness, we conducted a technical evaluation and a user study. Results show that ReFinE effectively synthesizes and contextualizes design implications, reducing cognitive load and improving designers' ability to integrate research evidence into UI mockups. This work contributes to bridging the gap between research and design practice by presenting a tool for embedding scholarly insights into the UI design process.

cs.HC↗

arXiv2026

CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints

Evaluating multi-paragraph clinical question answering (QA) systems is resource-intensive and challenging: accurate judgments require medical expertise and achieving consistent human judgments over multi-paragraph text is difficult. We introduce CQA-Eval, an evaluation framework and set of evaluation recommendations for limited-resource and high-expertise settings. Based on physician annotations of 300 real patient questions answered by physicians and LLMs, we compare coarse answer-level versus fine-grained sentence-level evaluation over the dimensions of correctness, relevance, and risk disclosure. We find that inter-annotator agreement (IAA) varies by dimension: fine-grained annotation improves agreement on correctness, coarse improves agreement on relevance, and judgments on communicates-risks remain inconsistent. Additionally, annotating only a small subset of sentences can provide reliability comparable to coarse annotations, reducing cost and effort.

cs.CL↗

arXiv2026

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension, typically data format or task type. We introduce MixAtlas, a method that produces benchmark-targeted data recipes that can be inspected, adapted, and transferred to new corpora. MixAtlas decomposes the training corpus along two axes: image concepts (10 visual-domain clusters discovered via CLIP embeddings) and task supervision (5 objective types including captioning, OCR, grounding, detection, and VQA). Using small proxy models (Qwen2-0.5B) paired with a Gaussian-process surrogate and GP-UCB acquisition, MixAtlas searches the resulting mixture space with the same proxy budget as regression-based baselines but finds better-performing mixtures. We evaluate on 10 benchmarks spanning visual understanding, document reasoning, and multimodal reasoning. On Qwen2-7B, optimized mixtures improve average performance by 8.5%-17.6% over the strongest baseline; on Qwen2.5-7B, gains are 1.0%-3.3%. Both settings reach baseline-equivalent training loss in up to 2 times fewer steps. Recipes discovered on 0.5B proxies transfer to 7B-scale training across Qwen model families.

cs.LG↗

arXiv2026

Deep Research, Shallow Evaluation: A Case Study in Meta-Evaluation for Long-Form QA Benchmarks

Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate these methods. Many of the meta-evaluations estimate an evaluation quality's by comparing its assessments against human pairwise preferences. Prior work, however, suggests that human pairwise preference may be overly simplistic and can fail to capture nuances of expert expectations. We conduct a case study in meta-evaluation for long-form QA benchmarks using ScholarQA-CS2, a benchmark designed for assessing retrieval-augmented deep-research QA in the scientific domain. We comprehensively validate the benchmark through human pairwise preference judgments, then critically examine the strengths, weaknesses, and confounders of this approach. We show that pairwise preference rankings are best suited for system-level evaluation, while explicit metric-wise annotations and expert annotators are critical for reliable metric-level assessment, with subjectivity remaining a key challenge. Based on our findings, we offer practical guidelines for designing future meta-evaluations that better align evaluation methods, annotator expertise, and reporting practices. By surfacing these methodological challenges, we aim to advance evaluation standards for deep-research systems.

cs.CL↗

arXiv2026

SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents

As LLM-based computer-use agents (CUAs) begin to autonomously interact with real-world interfaces, understanding their vulnerability to manipulative interface designs becomes increasingly critical. We introduce SusBench, an online benchmark for evaluating the susceptibility of CUAs to UI dark patterns, designs that aim to manipulate or deceive users into taking unintentional actions. Drawing nine common dark pattern types from existing taxonomies, we developed a method for constructing believable dark patterns on real-world consumer websites through code injections, and designed 313 evaluation tasks across 55 websites. Our study with 29 participants showed that humans perceived our dark pattern injections to be highly realistic, with the vast majority of participants not noticing that these had been injected by the research team. We evaluated five state-of-the-art CUAs on the benchmark. We found that both human participants and agents are particularly susceptible to the dark patterns of Preselection, Trick Wording, and Hidden Information, while being resilient to other overt dark patterns. Our findings inform the development of more trustworthy CUAs, their use as potential human proxies in evaluating deceptive designs, and the regulation of an online environment increasingly navigated by autonomous agents.

cs.HC↗

arXiv2026

Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification

Real-world visual question answering (VQA) is often context-dependent: an image-question pair may be under-specified, such that the correct answer depends on external information that is not observable in the image. In such cases, directly answering can lead to confident but incorrect predictions. We propose CoA(Clarify-or-Answer), an ask-or-answer agent that separately models the decision to ask or answer, and what to ask if needed. CoA first determines whether clarification is necessary; if so, it asks a single focused question and then incorporates the response to produce the final answer. We introduce CONTEXTCLARIFY with a set of ambiguous VQA questions and the contrast set that is non-ambiguous. We further introduce GRPO-CR (Clarification Reasoning), a reinforcement learning approach that optimizes clarification question generation with multiple reward signals encouraging well-formed, focused, non-trivial questions that resolve ambiguity. Across three VLLMs and three datasets, CoA achieves consistent improvements at both the module and system levels, improving end-to-end VQA accuracy by an average of +15.3 points (83%) over prompting-based baselines

cs.CL↗

arXiv2026

Passing the Buck to AI: How Individuals' Decision-Making Patterns Affect Reliance on AI

Psychological research has identified different patterns individuals have while making decisions, such as vigilance (making decisions after thorough information gathering), hypervigilance (rushed and anxious decision-making), and buckpassing (deferring decisions to others). We examine whether these decision-making patterns shape peoples' likelihood of seeking out or relying on AI. In an online experiment with 810 participants tasked with distinguishing food facts from myths, we found that a higher buckpassing tendency was positively correlated with both seeking out and relying on AI suggestions, while being negatively correlated with the time spent reading AI explanations. In contrast, the higher a participant tended towards vigilance, the more carefully they scrutinized the AI's information, as indicated by an increased time spent looking through the AI's explanations. These findings suggest that a person's decision-making pattern plays a significant role in their adoption and reliance on AI, which provides a new understanding of individual differences in AI-assisted decision-making.

cs.HC↗

arXiv2025

Leveraging Hierarchical Organization for Medical Multi-document Summarization

Medical multi-document summarization (MDS) is a complex task that requires effectively managing cross-document relationships. This paper investigates whether incorporating hierarchical structures in the inputs of MDS can improve a model's ability to organize and contextualize information across documents compared to traditional flat summarization methods. We investigate two ways of incorporating hierarchical organization across three large language models (LLMs), and conduct comprehensive evaluations of the resulting summaries using automated metrics, model-based metrics, and domain expert evaluation of preference, understandability, clarity, complexity, relevance, coverage, factuality, and coherence. Our results show that human experts prefer model-generated summaries over human-written summaries. Hierarchical approaches generally preserve factuality, coverage, and coherence of information, while also increasing human preference for summaries. Additionally, we examine whether simulated judgments from GPT-4 align with human judgments, finding higher agreement along more objective evaluation facets. Our findings demonstrate that hierarchical structures can improve the clarity of medical summaries generated by models while maintaining content coverage, providing a practical way to improve human preference for generated summaries.

cs.CL↗

arXiv2025

ROBoto2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment

We present ROBOTO2, an open-source, web-based platform for large language model (LLM)-assisted risk of bias (ROB) assessment of clinical trials. ROBOTO2 streamlines the traditionally labor-intensive ROB v2 (ROB2) annotation process via an interactive interface that combines PDF parsing, retrieval-augmented LLM prompting, and human-in-the-loop review. Users can upload clinical trial reports, receive preliminary answers and supporting evidence for ROB2 signaling questions, and provide real-time feedback or corrections to system suggestions. ROBOTO2 is publicly available at https://roboto2.vercel.app/, with code and data released to foster reproducibility and adoption. We construct and release a dataset of 521 pediatric clinical trial reports (8954 signaling questions with 1202 evidence passages), annotated using both manually and LLM-assisted methods, serving as a benchmark and enabling future research. Using this dataset, we benchmark ROB2 performance for 4 LLMs and provide an analysis into current model capabilities and ongoing challenges in automating this critical aspect of systematic review.

cs.CL↗

arXiv2025

Benchmarking PDF Accessibility Evaluation A Dataset and Framework for Assessing Automated and LLM-Based Approaches for Accessibility Testing

PDFs remain the dominant format for scholarly communication, despite significant accessibility challenges for blind and low-vision users. While various tools attempt to evaluate PDF accessibility, there is no standardized methodology to evaluate how different accessibility assessment approaches perform. Our work addresses this critical gap by introducing a novel benchmark dataset of scholarly PDFs with expert-validated accessibility annotations across seven criteria (alternative text quality, logical reading order, semantic tagging, table structure, functional hyperlinks, color contrast, and font readability), and a four-category evaluation framework with standardized labels (Passed, Failed, Not Present, Cannot Tell) to systematically assess accessibility evaluation approaches. Using our evaluation framework, we explore whether large language models (LLMs) are capable of supporting automated accessibility evaluation. We benchmark five LLMs, which demonstrate varying capabilities in correctly assessing different accessibility criteria, with GPT-4-Turbo achieving the highest overall accuracy (0.85). However, all models struggled in correctly categorizing documents with Not Present and Cannot Tell accessibility labels, particularly for alt text quality assessment. Our qualitative comparison with standard automated checkers reveals complementary strengths: rule-based tools excel at technical verification, while LLMs better evaluate semantic appropriateness and contextual relevance. Based on our findings, we propose a hybrid approach that would combine automated checkers, LLM evaluation, and human assessment as a future strategy for PDF accessibility evaluation.

cs.HC↗