EC
Eunsol Choi
cs.CLcs.AIcs.LGeess.AScs.SDcs.IRcs.HCcs.CVcs.CYcs.SE
On Valency
published · living versionsW_gsj4k5z2·v1 · currentpublished
Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models
with Anuj Diwan, David Harwath
1 version
W_63ejpxmg·v1published
Preprints & journals
89 papers in the corpus · 2012–2026Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment2609.38972v2 · Yihuai Hong, Shauli Ravfogel, Chen Zhao et al.2026 · 0 citationsarXiv
Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation2608.29887v1 · Nishant Balepur, Paiheng Xu, Wei Ai et al.2026 · 0 citationsarXiv
VibeJam: A User Study Platform for Web Development with Agents2608.29889v1 · Nishant Balepur, Connor Baumler, Valerie Chen et al.2026 · 0 citationsarXiv
(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding2607.26375v1 · Nishant Balepur, Connor Baumler, Valerie Chen et al.2026 · 0 citationsarXiv
Training Continuous Chain of Thought Models: A Tale of Two Regimes2607.16972v1 · Varun Yerram, He He, Eunsol Choi2026 · 0 citationsarXiv
DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute2604.23815v1 · Nishant Balepur, Malachi Hamada, Varsha Kishore et al.2026 · 0 citationsarXiv
No Single Best Model for Diversity: Learning a Router for Sample Diversity2604.02319v3 · Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar et al.2026 · 0 citationsarXiv
Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models2604.02485v1 · Ayush Rajesh Jhaveri, Anthony GX-Chen, Ilia Sucholutsky et al.2026 · 0 citationsarXiv
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining2603.28737v2 · Anuj Diwan, Eunsol Choi, David Harwath2026 · 0 citationsarXiv
Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users2603.16120v2 · Nishant Balepur, Malachi Hamada, Varsha Kishore et al.2026 · 0 citationsarXiv
Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph2603.15527v1 · Zhenheng Tang, Xiang Liu, Qian Wang et al.2026 · 0 citationsarXiv
Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads2602.22453v4 · Shaswat Patel, Vishvesh Trivedi, Yue Han et al.2026 · 0 citationsarXiv
RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering2602.18425v1 · Deniz Qian, Hung-Ting Chen, Eunsol Choi2026 · 0 citationsarXiv
DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning2602.18633v1 · Fangyuan Xu, Sihao Chen, Zinan Lin et al.2026 · 0 citationsarXiv
BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks2602.06221v2 · Nishant Balepur, Bhavya Rajasekaran, Jane Oh et al.2026 · 0 citationsarXiv
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback2601.18202v1 · Fangyuan Xu, Rujun Han, Yanfei Chen et al.2026 · 0 citationsarXiv
DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference2510.19669v5 · Xiang Liu, Xuming Hu, Xiaowen Chu et al.2025 · 0 citationsarXiv
User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal2507.23158v2 · Yuhan Liu, Michael J.Q. Zhang, Eunsol Choi2025 · 3 citationsarXiv
PropMEND: Hypernetworks for Knowledge Propagation in LLMs2506.08920v1 · Zeyu Leo Liu, Greg Durrett, Eunsol Choi2025 · 0 citationsarXiv
Learning to Reason Across Parallel Samples for LLM Reasoning2506.09014v2 · Jianing Qi, Xi Ye, Hao Tang et al.2025 · 0 citationsarXiv
Rhapsody: A Dataset for Highlight Detection in Podcasts2505.19429v2 · Younghan Park, Anuj Diwan, David Harwath et al.2025 · 0 citationsarXiv
On Language Models' Sensitivity to Suspicious Coincidences2504.09387v1 · Sriram Padmanabhan, Kanishka Misra, Kyle Mahowald et al.2025 · 0 citationsarXiv
Scaling Rich Style-Prompted Text-to-Speech Datasets2503.04713v2 · Anuj Diwan, Zhisheng Zheng, David Harwath et al.2025 · 4 citationsarXiv
Improving LLM-as-a-Judge Inference with the Judgment Distribution2503.03064v2 · Victor Wang, Michael J.Q. Zhang, Eunsol Choi2025 · 0 citationsarXiv
Future of Information Retrieval Research in the Age of Generative AI2412.02043v1 · James Allan, Eunsol Choi, Daniel P. Lopresti et al.2024 · 3 citationsarXiv
RefreshKV: Updating Small KV Cache During Long-form Generation2411.05787v2 · Fangyuan Xu, Tanya Goyal, Eunsol Choi2024 · 0 citationsarXiv
RARe: Retrieval Augmented Retrieval with In-Context Examples2410.20088v2 · Atula Tejaswi, Yoonsang Lee, Sujay Sanghavi et al.2024 · 0 citationsarXiv
Diverging Preferences: When do Annotators Disagree and do Models Know?2410.14632v3 · Michael JQ Zhang, Zhilin Wang, Jena D. Hwang et al.2024 · 0 citationsarXiv
Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions2410.13788v2 · Michael J.Q. Zhang, W. Bradley Knox, Eunsol Choi2024 · 1 citationarXiv
Contrastive Learning to Improve Retrieval for Real-world Fact Checking2410.04657v1 · Aniruddh Sriram, Fangyuan Xu, Eunsol Choi et al.2024 · 3 citationsarXiv
Open-World Evaluation for Retrieving Diverse Perspectives2409.18110v2 · Hung-Ting Chen, Eunsol Choi2024 · 0 citationsarXiv
CodeUpdateArena: Benchmarking Knowledge Editing on API Updates2407.06249v3 · Zeyu Leo Liu, Shrey Pandit, Xi Ye et al.2024 · 3 citationsarXiv
From Distributional to Overton Pluralism: Investigating Large Language Model Alignment2406.17692v2 · Thom Lake, Eunsol Choi, Greg Durrett2024 · 2 citationsarXiv
CaLMQA: Exploring culturally specific long-form question answering across 23 languages2406.17761v3 · Shane Arora, Marzena Karpinska, Hung-Ting Chen et al.2024 · 4 citationsarXiv
AmbigDocs: Reasoning across Documents on Different Entities under the Same Name2404.12447v3 · Yoonsang Lee, Xi Ye, Eunsol Choi2024 · 1 citationarXiv
KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions2403.03866v1 · Fangyuan Xu, Kyle Lo, Luca Soldaini et al.2024 · 3 citationsarXiv
BAT: Learning to Reason about Spatial Sounds with Large Language Models2402.01591v4 · Zhisheng Zheng, Puyuan Peng, Ziyang Ma et al.2024 · 3 citationsarXiv
Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs2311.09469v1 · Michael J.Q. Zhang, Eunsol Choi2023 · 18 citationsarXiv
Crafting In-context Examples according to LMs' Parametric Knowledge2311.09579v2 · Yoonsang Lee, Pranav Atreya, Xi Ye et al.2023 · 2 citationsarXiv
Understanding Retrieval Augmentation for Long-Form Question Answering2310.12150v2 · Hung-Ting Chen, Fangyuan Xu, Shane Arora et al.2023 · 3 citationsarXiv
Development and Evaluation of Three Chatbots for Postpartum Mood and Anxiety Disorders2308.07407v1 · Xuewen Yao, Miriam Mikhelson, S. Craig Watkins et al.2023 · 9 citationsarXiv
Propagating Knowledge Updates to LMs Through Distillation2306.09306v2 · Shankar Padmanabhan, Yasumasa Onoe, Michael J.Q. Zhang et al.2023 · 4 citationsarXiv
When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants2306.08667v1 · Anuj Diwan, Eunsol Choi, David Harwath2023 · 2 citationsarXiv
Concise Answers to Complex Questions: Summarization of Long-form Answers2305.19271v1 · Abhilash Potluri, Fangyuan Xu, Eunsol Choi2023 · 4 citationsarXiv
A Critical Evaluation of Evaluations for Long-form Question Answering2305.18201v1 · Fangyuan Xu, Yixiao Song, Mohit Iyyer et al.2023 · 33 citationsarXiv
Mitigating Temporal Misalignment by Discarding Outdated Facts2305.14824v3 · Michael J.Q. Zhang, Eunsol Choi2023 · 6 citationsarXiv
Textless Speech-to-Speech Translation With Limited Parallel Data2305.15405v3 · Anuj Diwan, Anirudh Srinivasan, David Harwath et al.2023 · 3 citationsarXiv
Continually Improving Extractive QA via Human Feedback2305.12473v2 · Ge Gao, Hung-Ting Chen, Yoav Artzi et al.2023 · 5 citationsarXiv
Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge2305.01651v1 · Yasumasa Onoe, Michael J.Q. Zhang, Shankar Padmanabhan et al.2023 · 27 citationsarXiv
DIFFQG: Generating Questions to Summarize Factual Changes2303.00242v1 · Jeremy R. Cole, Palak Jain, Julian Martin Eisenschlos et al.2023 · 0 citationsarXiv
Career total: 112 works. 89 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.