A survey of large language models

WX Zhao, K Zhou, J Li, T Tang, X Wang, Y Hou… - arxiv preprint arxiv …, 2023 - arxiv.org
Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …

The flan collection: Designing data and methods for effective instruction tuning

S Longpre, L Hou, T Vu, A Webson… - International …, 2023 - proceedings.mlr.press
We study the design decision of publicly available instruction tuning methods, by
reproducing and breaking down the development of Flan 2022 (Chung et al., 2022) …

Siren's song in the AI ocean: a survey on hallucination in large language models

Y Zhang, Y Li, L Cui, D Cai, L Liu, T Fu… - arxiv preprint arxiv …, 2023 - arxiv.org
While large language models (LLMs) have demonstrated remarkable capabilities across a
range of downstream tasks, a significant concern revolves around their propensity to exhibit …

In-context retrieval-augmented language models

O Ram, Y Levine, I Dalmedigos, D Muhlgay… - Transactions of the …, 2023 - direct.mit.edu
Abstract Retrieval-Augmented Language Modeling (RALM) methods, which condition a
language model (LM) on relevant documents from a grounding corpus during generation …

Benchmarking large language models for news summarization

T Zhang, F Ladhak, E Durmus, P Liang… - Transactions of the …, 2024 - direct.mit.edu
Large language models (LLMs) have shown promise for automatic summarization but the
reasons behind their successes are poorly understood. By conducting a human evaluation …

Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models

P Manakul, A Liusie, MJF Gales - arxiv preprint arxiv:2303.08896, 2023 - arxiv.org
Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly
fluent responses to a wide variety of user prompts. However, LLMs are known to hallucinate …