arXiv subjects

Jennifer Healey

Publications and source records attributed to Jennifer Healey.

At least 19 recordsLinked to original sources

arXiv2026

LinkNav: Surfacing Interconnected Information in Scientific Articles

We present LinkNav, an enhanced experience for reading academic papers which makes explicit connections between related but non-adjacent passages. To create the experience, we instruct a language model to generate questions that may arise while reading a passage and then search for answer passages elsewhere in the document, forming intra-document connections when answers are found. We confirm that these building blocks work well to power the experience, with an answer detection pipeline that works with high precision, resulting in a reasonable number of connections being made for a document. On a dataset of academic papers, we find that connected passages are on average ten segments away from each other, making explicit connections that a reader may have otherwise missed.

cs.HC↗

arXiv2026

Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA

Pluralistic alignment requires systems to adapt to diverse user values, communication styles, and contextual assumptions. We believe that a foundational prerequisite for such alignment enabling accurate preference elicitation from people when their intent is under-specified or ambiguous. We study the problem of preference elicitation in multi-turn question answering by decomposing the problem into two components: a \textbf{clarification policy}, which decides whether to ask a clarifying question or answer directly, and \textbf{post-clarification answering}, which produces the correct final answer once the missing information is provided. We show, using the PACIFIC benchmark, that supervised fine-tuning rapidly improves the clarification policy, however, final answer accuracy remains substantially lower even when the model takes the correct action. This gap indicates that understanding and correctly interpreting the user's response is the critical gap in multi-turn question-answering systems.

cs.CL↗

arXiv2026

Budgeted Online Influence Maximization

We introduce a new budgeted framework for online influence maximization, considering the total cost of an advertising campaign instead of the common cardinality constraint on a chosen influencer set. Our approach better models the real-world setting where the cost of influencers varies and advertisers want to find the best value for their overall social advertising budget. We propose an algorithm assuming an independent cascade diffusion model and edge level semi-bandit feedback, and provide both theoretical and experimental results. Our analysis is also valid for the cardinality constraint setting and improves the state of the art regret bound in this case.

cs.LG↗

arXiv2026

Scale-free adaptive planning for deterministic dynamics & discounted rewards

We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value function is not known, nor are the rewards bounded. We propose Platypoos, a simple scale-free planning algorithm that adapts to the unknown scale and smoothness of the reward function. We provide a sample complexity analysis for Platypoos that improves upon prior work and holds simultaneously over a broad range of discount factors and reward scales, without the algorithm knowing them. We also establish a matching lower bound showing our analysis is optimal up to constants.

cs.LG↗

arXiv2025

Multi-Hop Question Answering: When Can Humans Help, and Where do They Struggle?

Multi-hop question answering is a challenging task for both large language models (LLMs) and humans, as it requires recognizing when multi-hop reasoning is needed, followed by reading comprehension, logical reasoning, and knowledge integration. To better understand how humans might collaborate effectively with AI, we evaluate the performance of crowd workers on these individual reasoning subtasks. We find that while humans excel at knowledge integration (97\% accuracy), they often fail to recognize when a question requires multi-hop reasoning (67\% accuracy). Participants perform reasonably well on both single-hop and multi-hop QA (84\% and 80\% accuracy, respectively), but frequently make semantic mistakes--for example, answering "when" an event happened when the question asked "where." These findings highlight the importance of designing AI systems that complement human strengths while compensating for common weaknesses.

cs.HC↗

arXiv2025

Quantitative LLM Judges

LLM-as-a-judge is a framework where a large language model (LLM) evaluates the output of another LLM. While LLMs excel at producing qualitative textual evaluations, they often struggle to predict human preferences and numeric scores. We propose quantitative LLM judges, which align evaluation scores of existing LLM judges to humans in a given domain using regression models. The models are trained to improve the score of the original judge using its rationale and score. We present four quantitative judges for different types of absolute and relative feedback, which showcases the generality and versatility of our framework. Our framework is more computationally efficient than supervised fine-tuning and can be more statistically efficient when human feedback is limited, which is expected in practice. We validate these claims empirically on four datasets using two base judges. Our experiments show that quantitative judges can improve the predictive power of existing judges through post-hoc modeling.

cs.CL↗

arXiv2025

Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries

While large language models (LLMs) are increasingly capable of handling longer contexts, recent work has demonstrated that they exhibit the "lost in the middle" phenomenon (Liu et al., 2024) of unevenly attending to different parts of the provided context. This hinders their ability to cover diverse source material in multi-document summarization, as noted in the DiverseSumm benchmark (Huang et al., 2024). In this work, we contend that principled content selection is a simple way to increase source coverage on this task. As opposed to prompting an LLM to perform the summarization in a single step, we explicitly divide the task into three steps -- (1) reducing document collections to atomic key points, (2) using determinantal point processes (DPP) to perform select key points that prioritize diverse content, and (3) rewriting to the final summary. By combining prompting steps, for extraction and rewriting, with principled techniques, for content selection, we consistently improve source coverage on the DiverseSumm benchmark across various LLMs. Finally, we also show that by incorporating relevance to a provided user intent into the DPP kernel, we can generate personalized summaries that cover relevant source information while retaining coverage.

cs.CL↗

arXiv2025

Developing A Framework to Support Human Evaluation of Bias in Generated Free Response Text

LLM evaluation is challenging even the case of base models. In real world deployments, evaluation is further complicated by the interplay of task specific prompts and experiential context. At scale, bias evaluation is often based on short context, fixed choice benchmarks that can be rapidly evaluated, however, these can lose validity when the LLMs' deployed context differs. Large scale human evaluation is often seen as too intractable and costly. Here we present our journey towards developing a semi-automated bias evaluation framework for free text responses that has human insights at its core. We discuss how we developed an operational definition of bias that helped us automate our pipeline and a methodology for classifying bias beyond multiple choice. We additionally comment on how human evaluation helped us uncover problematic templates in a bias benchmark.

cs.CL↗

arXiv2025

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Large language models (LLMs) are increasingly optimized for long reasoning, under the assumption that more reasoning leads to better performance. However, emerging evidence suggests that longer responses can sometimes degrade accuracy rather than improve it. In this paper, we conduct a systematic empirical study of the relationship between reasoning length and answer correctness. We find that LLMs tend to overthink simple problems, generating unnecessarily long outputs, and underthink harder ones, failing to extend their reasoning when it is most needed. This indicates that models might misjudge problem difficulty and fail to calibrate their response length appropriately. Furthermore, we investigate the effects of length reduction with a preference optimization algorithm when simply preferring the shorter responses regardless of answer correctness. Experiments show that the generation length can be significantly reduced while maintaining acceptable accuracy. Our findings highlight generation length as a meaningful signal for reasoning behavior and motivate further exploration into LLMs' self-awareness in reasoning length adaptation.

cs.CL↗

arXiv2025

Since U Been Gone: Augmenting Context-Aware Transcriptions for Re-engaging in Immersive VR Meetings

Maintaining engagement in immersive meetings is challenging, particularly when users must catch up on missed content after disruptions. While transcription interfaces can help, table-fixed panels have the potential to distract users from the group, diminishing social presence, while avatar-fixed captions fail to provide past context. We present EngageSync, a context-aware avatar-fixed transcription interface that adapts based on user engagement, offering live transcriptions and LLM-generated summaries to enhance catching up while preserving social presence. We implemented a live VR meeting setup for a 12-participant formative study and elicited design considerations. In two user studies with small (3 avatars) and mid-sized (7 avatars) groups, EngageSync significantly improved social presence (p < .05) and time spent gazing at others in the group instead of the interface over table-fixed panels. Also, it reduced re-engagement time and increased information recall (p < .05) over avatar-fixed interfaces, with stronger effects in mid-sized groups (p < .01).

cs.HC↗

arXiv2025

Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model (LLM) hallucinations by incorporating external knowledge retrieval. However, existing RAG frameworks often apply retrieval indiscriminately,leading to inefficiencies-over-retrieving when unnecessary or failing to retrieve iteratively when required for complex reasoning. Recent adaptive retrieval strategies, though adaptively navigates these retrieval strategies, predict only based on query complexity and lacks user-driven flexibility, making them infeasible for diverse user application needs. In this paper, we introduce a novel user-controllable RAG framework that enables dynamic adjustment of the accuracy-cost trade-off. Our approach leverages two classifiers: one trained to prioritize accuracy and another to prioritize retrieval efficiency. Via an interpretable control parameter $\alpha$, users can seamlessly navigate between minimal-cost retrieval and high-accuracy retrieval based on their specific requirements. We empirically demonstrate that our approach effectively balances accuracy, retrieval cost, and user controllability, making it a practical and adaptable solution for real-world applications. Code is available at https://github.com/JinyanSu1/Flare-Aug.

cs.IR↗

arXiv2024

TextLap: Customizing Language Models for Text-to-Layout Planning

Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for image generation and graphical design benchmarks.

cs.CL↗

arXiv2024

Evaluating Nuanced Bias in Large Language Model Free Response Answers

Pre-trained large language models (LLMs) can now be easily adapted for specific business purposes using custom prompts or fine tuning. These customizations are often iteratively re-engineered to improve some aspect of performance, but after each change businesses want to ensure that there has been no negative impact on the system's behavior around such critical issues as bias. Prior methods of benchmarking bias use techniques such as word masking and multiple choice questions to assess bias at scale, but these do not capture all of the nuanced types of bias that can occur in free response answers, the types of answers typically generated by LLM systems. In this paper, we identify several kinds of nuanced bias in free text that cannot be similarly identified by multiple choice tests. We describe these as: confidence bias, implied bias, inclusion bias and erasure bias. We present a semi-automated pipeline for detecting these types of bias by first eliminating answers that can be automatically classified as unbiased and then co-evaluating name reversed pairs using crowd workers. We believe that the nuanced classifications our method generates can be used to give better feedback to LLMs, especially as LLM reasoning capabilities become more advanced.

cs.CL↗

arXiv2024

Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Models

Recent advancements in instruction-following models have made user interactions with models more user-friendly and efficient, broadening their applicability. In graphic design, non-professional users often struggle to create visually appealing layouts due to limited skills and resources. In this work, we introduce a novel multimodal instruction-following framework for layout planning, allowing users to easily arrange visual elements into tailored layouts by specifying canvas size and design purpose, such as for book covers, posters, brochures, or menus. We developed three layout reasoning tasks to train the model in understanding and executing layout instructions. Experiments on two benchmarks show that our method not only simplifies the design process for non-professionals but also surpasses the performance of few-shot GPT-4V models, with mIoU higher by 12% on Crello. This progress highlights the potential of multimodal instruction-following models to automate and simplify the design process, providing an approachable solution for a wide range of design tasks on visually-rich documents.

cs.CV↗

arXiv2024

DocuBits: VR Document Decomposition for Procedural Task Completion

Reading monolithic instructional documents in VR is often challenging, especially when tasks are collaborative. Here we present DocuBits, a novel method for transforming monolithic documents into small, interactive instructional elements. Our approach allows users to:(i) create instructional elements (ii) position them within VR and (iii) use them to monitor and share progress in a multi-user VR learning environment. We describe our design methodology as well as two user studies evaluating how both individual users and pairs of users interact with DocuBits compared to monolithic documents while performing a chemistry lab task. Our analysis shows that, for both studies, DocuBits had substantially higher usability, while decreasing perceived workload (p < 0.001$. Our collaborative study showed that participants perceived higher social presence, collaborator awareness as well as immersion and presence (p < 0.001). We discuss our insights for using text-based instructions to support enhanced collaboration in VR environments.

cs.HC↗

arXiv2023

PaperToPlace: Transforming Instruction Documents into Spatialized and Context-Aware Mixed Reality Experiences

While paper instructions are one of the mainstream medium for sharing knowledge, consuming such instructions and translating them into activities are inefficient due to the lack of connectivity with physical environment. We present PaperToPlace, a novel workflow comprising an authoring pipeline, which allows the authors to rapidly transform and spatialize existing paper instructions into MR experience, and a consumption pipeline, which computationally place each instruction step at an optimal location that is easy to read and do not occlude key interaction areas. Our evaluations of the authoring pipeline with 12 participants demonstrated the usability of our workflow and the effectiveness of using a machine learning based approach to help extracting the spatial locations associated with each steps. A second within-subject study with another 12 participants demonstrates the merits of our consumption pipeline by reducing efforts of context switching, delivering the segmented instruction steps and offering the hands-free affordances.

cs.HC↗

arXiv2023

Experts prefer text but videos help novices: an analysis of the utility of multi-media content

Multi-media increases engagement and is increasingly prevalent in online content including news, web blogs, and social media, however, it may not always be beneficial to users. To determine what types of media users actually wanted, we conducted an exploratory study where users got to choose their own media augmentation. Our findings showed that users desired different amounts and types of media depending on their familiarity with the content. To further investigate this difference, we created two versions of a media augmented document, one designed for novices and one designed for experts. We evaluated these prototypes in a two-way between-subject study with 48 participants and found that while multi-media enhanced novice readers' perception of usability (p = .0100) and helped them with reading time (p = .0427), time on task (p= .0156), comprehension (p = .0161), experts largely ignored multi-media and primarily utilized text.

cs.HC↗

arXiv2022

VRDoc: Gaze-based Interactions for VR Reading Experience

Virtual reality (VR) offers the promise of an infinite office and remote collaboration, however, existing interactions in VR do not strongly support one of the most essential tasks for most knowledge workers, reading. This paper presents VRDoc, a set of gaze-based interaction methods designed to improve the reading experience in VR. We introduce three key components: Gaze Select-and-Snap for document selection, Gaze MagGlass for enhanced text legibility, and Gaze Scroll for ease of document traversal. We implemented each of these tools using a commodity VR headset with eye-tracking. In a series of user studies with 13 participants, we show that VRDoc makes VR reading both more efficient (p < 0.01 ) and less demanding (p < 0.01), and when given a choice, users preferred to use our tools over the current VR reading methods.

cs.HC↗