626 citations · 1.7k across the 87 of their papers we have counts for
16 papers · 1 filter
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…
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…
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)…
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…
PaRaDe: Passage Ranking using Demonstrations with Large Language Models
Andrew Drozdov, Honglei Zhuang, Zhuyun Dai +8
Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method,…
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…
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…
A Critical Evaluation of Evaluations for Long-form Question Answering
Fangyuan Xu, Yixiao Song, Mohit Iyyer +1
Long-form question answering (LFQA) enables answering a wide range of questions, but its flexibility poses enormous challenges for evaluation. We perform the first targeted study o…
KNN-LM Does Not Improve Open-ended Text Generation
Shufan Wang, Yixiao Song, Andrew Drozdov +3
In this paper, we study the generation quality of interpolation-based retrieval-augmented language models (LMs). These methods, best exemplified by the KNN-LM, interpolate the LM's…
PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Simeng Sun, Yang Liu, Shuohang Wang +2
Strategies such as chain-of-thought prompting improve the performance of large language models (LLMs) on complex reasoning tasks by decomposing input examples into intermediate ste…
Large language models effectively leverage document-level context for literary translation, but critical errors persist
Marzena Karpinska, Mohit Iyyer
Large language models (LLMs) are competitive with the state of the art on a wide range of sentence-level translation datasets. However, their ability to translate paragraphs and do…
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
Sewon Min, Kalpesh Krishna, Xinxi Lyu +6
Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pie…
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Kalpesh Krishna, Yixiao Song, Marzena Karpinska +2
The rise in malicious usage of large language models, such as fake content creation and academic plagiarism, has motivated the development of approaches that identify AI-generated…
Stealing the Decoding Algorithms of Language Models
Ali Naseh, Kalpesh Krishna, Mohit Iyyer +1
A key component of generating text from modern language models (LM) is the selection and tuning of decoding algorithms. These algorithms determine how to generate text from the int…
How Does In-Context Learning Help Prompt Tuning?
Simeng Sun, Yang Liu, Dan Iter +2
Fine-tuning large language models is becoming ever more impractical due to their rapidly-growing scale. This motivates the use of parameter-efficient adaptation methods such as pro…
LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
Kalpesh Krishna, Erin Bransom, Bailey Kuehl +4
While human evaluation remains best practice for accurately judging the faithfulness of automatically-generated summaries, few solutions exist to address the increased difficulty a…