Mohit Iyyer
University of Massachusetts Amherst
H-index: 36
North America-United States
Top articles of Mohit Iyyer
Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
arXiv preprint arXiv:2404.13784
2024/4/21
FABLES: Evaluating faithfulness and content selection in book-length summarization
arXiv preprint arXiv:2404.01261
2024/4/1
Marzena Karpinska
H-Index: 2
Mohit Iyyer
H-Index: 21
Gee! grammar error explanation with large language models
2024
TopicGPT: A prompt-based topic modeling framework
arXiv preprint arXiv:2311.01449
2023/11/2
BooookScore: A systematic exploration of book-length summarization in the era of LLMs
2024
Mohit Iyyer
H-Index: 21
PaRaDe: Passage Ranking using Demonstrations with LLMs
2023/12/1
A Framework for Exploring Player Perceptions of LLM-Generated Dialogue in Commercial Video Games
2023/12
Multistage Collaborative Knowledge Distillation from Large Language Models
arXiv preprint arXiv:2311.08640
2023/11/15
Freshllms: Refreshing large language models with search engine augmentation
arXiv preprint arXiv:2310.03214
2023/10/5
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of rlhf
arXiv preprint arXiv:2309.09055
2023/9/16
A critical evaluation of evaluations for long-form question answering
2023/5/29
Mohit Iyyer
H-Index: 21
KNN-LM Does Not Improve Open-ended Text Generation
2023/5/24
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
arXiv preprint arXiv:2305.14251
2023/5/23
Large language models effectively leverage document-level context for literary translation, but critical errors persist
2023/4/6
Marzena Karpinska
H-Index: 2
Mohit Iyyer
H-Index: 21
Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense
2023/3/23
Stealing the Decoding Algorithms of Language Models
2023/3/8
How does in-context learning help prompt tuning?
arXiv preprint arXiv:2302.11521
2023/2/22
LongEval: Guidelines for human evaluation of faithfulness in long-form summarization
2023/1/30
Kalpesh Krishna
H-Index: 7
Mohit Iyyer
H-Index: 21
PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
arXiv preprint arXiv:2305.14564
2023/5/23
Towards Grounded Dialogue Generation in Video Game Environments
Creative AI Across Modalities Workshop, AAAI
2023
Nader Akoury
H-Index: 3
Mohit Iyyer
H-Index: 21