activity
20222026
most citedRECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation

12 citations · 18 across the 11 of their papers we have counts for

collaborators

11 papers

cs.CL2026

No Single Best Model for Diversity: Learning a Router for Sample Diversity

Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar +2

When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide range of users. In this paper, we s…

cs.CL2024

RefreshKV: Updating Small KV Cache During Long-form Generation

Fangyuan Xu, Tanya Goyal, Eunsol Choi

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up app…

cs.CL2024★ 1 cited

Contrastive Learning to Improve Retrieval for Real-world Fact Checking

Aniruddh Sriram, Fangyuan Xu, Eunsol Choi +1

Recent work on fact-checking addresses a realistic setting where models incorporate evidence retrieved from the web to decide the veracity of claims. A bottleneck in this pipeline…

cs.CL2024★ 1 cited

Long-Form Answers to Visual Questions from Blind and Low Vision People

Mina Huh, Fangyuan Xu, Yi-Hao Peng +5

Vision language models can now generate long-form answers to questions about images - long-form visual question answers (LFVQA). We contribute VizWiz-LF, a dataset of long-form ans…

cs.CL2024

KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions

Fangyuan Xu, Kyle Lo, Luca Soldaini +3

Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly common instruction-foll…

cs.CL2023★ 12 cited

RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation

Fangyuan Xu, Weijia Shi, Eunsol Choi

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spannin…