activity
20162026
most citedParaphrasing evades detectors of AI-generated text, but retrieval is an effective defense

91 citations · 357 across the 71 of their papers we have counts for

collaborators
Showing 2023 · cs.CLShow all

14 papers · 2 filters

cs.CL2023★ 7 cited

FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation

Tu Vu, Mohit Iyyer, Xuezhi Wang +8

Most large language models (LLMs) are trained once and never updated; thus, they lack the ability to dynamically adapt to our ever-changing world. In this work, we perform a detail…

cs.CL2023★ 2 cited

GEE! Grammar Error Explanation with Large Language Models

Yixiao Song, Kalpesh Krishna, Rajesh Bhatt +2

Grammatical error correction tools are effective at correcting grammatical errors in users' input sentences but do not provide users with \textit{natural language} explanations abo…

cs.CL2023

Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

Jiachen Zhao, Wenlong Zhao, Andrew Drozdov +5

We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs)…

cs.CL2023★ 12 cited

TopicGPT: A Prompt-based Topic Modeling Framework

Chau Minh Pham, Alexander Hoyle, Simeng Sun +2

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the t…

cs.CL2023★ 14 cited

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

Yapei Chang, Kyle Lo, Tanya Goyal +1

Summarizing book-length documents (>100K tokens) that exceed the context window size of large language models (LLMs) requires first breaking the input document into smaller chunks…

cs.CL2023

Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF

Simeng Sun, Dhawal Gupta, Mohit Iyyer

During the last stage of RLHF, a large language model is aligned to human intents via PPO training, a process that generally requires large-scale computational resources. In this t…