Tool learning with foundation models

Y Qin, S Hu, Y Lin, W Chen, N Ding, G Cui… - ACM Computing …, 2024 - dl.acm.org
Humans possess an extraordinary ability to create and utilize tools. With the advent of
foundation models, artificial intelligence systems have the potential to be equally adept in …

Woodpecker: Hallucination correction for multimodal large language models

S Yin, C Fu, S Zhao, T Xu, H Wang, D Sui… - Science China …, 2024 - Springer
Hallucinations is a big shadow hanging over the rapidly evolving multimodal large language
models (MLLMs), referring to that the generated text is inconsistent with the image content …

Enabling large language models to generate text with citations

T Gao, H Yen, J Yu, D Chen - arxiv preprint arxiv:2305.14627, 2023 - arxiv.org
Large language models (LLMs) have emerged as a widely-used tool for information
seeking, but their generated outputs are prone to hallucination. In this work, our aim is to …

Factuality enhanced language models for open-ended text generation

N Lee, W **, P Xu, M Patwary… - Advances in …, 2022 - proceedings.neurips.cc
Pretrained language models (LMs) are susceptible to generate text with nonfactual
information. In this work, we measure and improve the factual accuracy of large-scale LMs …

Dense text retrieval based on pretrained language models: A survey

WX Zhao, J Liu, R Ren, JR Wen - ACM Transactions on Information …, 2024 - dl.acm.org
Text retrieval is a long-standing research topic on information seeking, where a system is
required to return relevant information resources to user's queries in natural language. From …

Autoregressive search engines: Generating substrings as document identifiers

M Bevilacqua, G Ottaviano, P Lewis… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Knowledge-intensive language tasks require NLP systems to both provide the
correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive …

Rarr: Researching and revising what language models say, using language models

L Gao, Z Dai, P Pasupat, A Chen, AT Chaganty… - arxiv preprint arxiv …, 2022 - arxiv.org
Language models (LMs) now excel at many tasks such as few-shot learning, question
answering, reasoning, and dialog. However, they sometimes generate unsupported or …

Internet-augmented language models through few-shot prompting for open-domain question answering

A Lazaridou, E Gribovskaya, W Stokowiec… - arxiv preprint arxiv …, 2022 - arxiv.org
In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language
models (LSLMs) to overcome some of their challenges with respect to grounding to factual …

Re2G: Retrieve, rerank, generate

M Glass, G Rossiello, MFM Chowdhury… - arxiv preprint arxiv …, 2022 - arxiv.org
As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces
become larger and larger. However, for tasks that require a large amount of knowledge, non …

Temporalwiki: A lifelong benchmark for training and evaluating ever-evolving language models

J Jang, S Ye, C Lee, S Yang, J Shin, J Han… - arxiv preprint arxiv …, 2022 - arxiv.org
Language Models (LMs) become outdated as the world changes; they often fail to perform
tasks requiring recent factual information which was absent or different during training, a …