update paper statuses

Author: Keyu-He

_bibliography/papers.bib

@@ -17,18 +17,18 @@ @article{keyu2025explanations
   title={ELI-Why: Evaluating the Pedagogical Utility of LLM Explanations},
   author={Brihi Joshi* and Keyu He* and Sahana Ramnath and Sadra Sabouri and Kaitlyn Zhou and Souti Chattopadhyay and Swabha Swayamdipta and Xiang Ren},
   year={2025},
-  journal={Submitted to ACL, Under review},
+  journal={ACL Findings 2025},
   abstract={Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explored. To this end, we introduce ELI-WHY, a benchmark of 13.4K "Why" questions to assess the pedagogical capabilities of LLMs. We then conduct two extensive human studies to assess the utility of LLM-generated explanatory answers (explanations) on our benchmark, tailored to three distinct educational grades: elementary, high-school, and graduate school. In our first study, human raters assume the role of an "educator" to assess model explanations' fit to different educational grades. We find that GPT-4-generated explanations match their intended educational background only 50% of the time, compared to 79% for human-curated explanations. In our second study, human raters assume the role of a learner to assess if an explanation fits their own informational needs. Results show that users deemed GPT-4-generated explanations relatively 20% less suited to their informational needs, particularly for advanced learners. Additionally, automated evaluation metrics reveal that GPT-4 explanations for different informational needs remain indistinguishable in their grade-level, limiting their pedagogical effectiveness. These findings suggest that LLMs' ability to follow inference-time instructions alone is insufficient for producing high-utility explanations tailored to users' informational needs.},
   selected={true},
   pdf={ELI_Why_Evaluating_the_Pe.pdf}
 }
 
 @article{keyu2025vlm,
   title={Beyond the Text: How Explanation Qualities Influence User Trust in Visual Language Models},
-  author={Keyu He and Brihi Joshi and Tejas Srinivasan and Swabha Swayamdipta},
+  author={Keyu He and Tejas Srinivasan and Brihi Joshi and Xiang Ren and Jesse Thomason and Swabha Swayamdipta},
   year={2025},
-  journal={Under preparation for NeurIPS},
-  abstract={Visual Language Models (VLMs) are deployed in scenarios where users lack direct access to visual stimuli, such as remote sensing, robotics, and assistance for people with visual impairments. Despite their utility, these models can produce hallucinated outputs that may mislead users. In this work, we investigate the role of explanation quality in calibrating user trust and reliance on VLM outputs. We propose new qualities, Visual Fidelity and Contrastiveness, to complement traditional text-only measures. Through quantitative evaluations on A-OKVQA and VizWiz datasets and a user study, our results indicate that explanations enriched with quality signals lead to a lower unsure rate and improved prediction accuracy and utility in AI-assisted decision-making. We also highlight limitations and future directions to further enhance the interpretability and reliability of VLM-generated rationales.},
+  journal={Submitted to NeurIPS, Under Review},
+  abstract={When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural language explanations can signal which model predictions are reliable. However, prior work has found that explanations can easily convince users that inaccurate VLM predictions are correct. To remedy undesirable overreliance on VLM predictions, we propose evaluating two complementary qualities of VLM-generated explanations via two quality scoring functions. We propose Visual Fidelity, which captures how faithful an explanation is to the visual context, and Contrastiveness, which captures how well the explanation identifies visual details that distinguish the model’s prediction from plausible alternatives. On the A-OKVQA and VizWiz tasks, these quality scoring functions are better calibrated with model correctness than existing explanation qualities. We conduct a user study in which participants have to decide whether a VLM prediction is accurate without viewing its visual context. We observe that showing our quality scores alongside VLM explanations improves participants’ accuracy at predicting VLM correctness by 11.1%, including a 15.4% reduction in the rate of falsely believing incorrect predictions. These findings highlight the utility of explanation quality scores in fostering appropriate reliance on VLM predictions.},
   selected={true}
 }
 

assets/json/resume.json

@@ -50,17 +50,17 @@
     {
       "name": "ELI-Why: Evaluating the Pedagogical Utility of LLM Explanations",
       "author": "Brihi Joshi*, <b>Keyu He*</b>, Sahana Ramnath, Sadra Sabouri, Kaitlyn Zhou, Souti Chattopadhyay, Swabha Swayamdipta, Xiang Ren",
-      "publisher": "Submitted to ACL 2025",
+      "publisher": "ACL Findings 2025",
       "releaseDate": "2025-02",
       "summary": "Evaluate the pedagogical utility of LLMs in tailoring explanations to users with different educational backgrounds.",
       "url": "../assets/pdf/ELI_Why_Evaluating_the_Pe.pdf"
     },
     {
       "name": "Beyond the Text: How Explanation Qualities Influence User Trust in Visual Language Models",
-      "author": "Keyu He, Brihi Joshi, Tejas Srinivasan, Swabha Swayamdipta",
-      "publisher": "(in preparation for NeurIPS submission)",
+      "author": "Keyu He, Tejas Srinivasan, Brihi Joshi, Xiang Ren, Jesse Thomason, Swabha Swayamdipta",
+      "publisher": "Submitted to NeurIPS 2025",
       "releaseDate": "2025-02",
-      "summary": "Identify limitations of current text-only metric and explore new vision-specific qualities to improve trust in explanations by VLMs."
+      "summary": "We introduce Visual Fidelity and Contrastiveness -- two explanation quality scores that help users more appropriately rely on vision-language model predictions without seeing the image."
     },
     {
       "name": "Attributing Culture-Conditioned Generations to Pretraining Corpora",