Improving Attributed Text Generation of Large Language Models via Preference Learning
- URL: http://arxiv.org/abs/2403.18381v1
- Date: Wed, 27 Mar 2024 09:19:13 GMT
- Title: Improving Attributed Text Generation of Large Language Models via Preference Learning
- Authors: Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang,
- Abstract summary: We model the attribution task as preference learning and introduce an Automatic Preference Optimization framework.
APO achieves state-of-the-art citation F1 with higher answer quality.
- Score: 28.09715554543885
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality.
Related papers
- Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences.
Our key idea is leveraging the human prior knowledge within the small (seed) data.
We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
arXiv Detail & Related papers (2024-06-06T18:01:02Z) - Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation [65.16137964758612]
We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books.
Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text.
arXiv Detail & Related papers (2024-05-31T20:15:10Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [90.4820014819937]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when finetuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - Optimizing Language Models for Human Preferences is a Causal Inference Problem [41.59906798328058]
We present an initial exploration of language model optimization for human preferences from direct outcome datasets.
We first propose that language model optimization should be viewed as a causal problem to ensure that the model correctly learns the relationship between the text and the outcome.
We extend CPO with doubly robust CPO, which reduces the variance of the surrogate objective while retaining provably strong guarantees on bias.
arXiv Detail & Related papers (2024-02-22T21:36:07Z) - Reranking for Natural Language Generation from Logical Forms: A Study
based on Large Language Models [47.08364281023261]
Large language models (LLMs) have demonstrated impressive capabilities in natural language generation.
However, their output quality can be inconsistent, posing challenges for generating natural language from logical forms (LFs)
arXiv Detail & Related papers (2023-09-21T17:54:58Z) - Enabling Large Language Models to Generate Text with Citations [37.64884969997378]
Large language models (LLMs) have emerged as a widely-used tool for information seeking.
Our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability.
We propose ALCE, the first benchmark for Automatic LLMs' Citation Evaluation.
arXiv Detail & Related papers (2023-05-24T01:53:49Z) - AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks.
We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate.
We build the first conversation-based information retrieval dataset employing AnnoLLM.
arXiv Detail & Related papers (2023-03-29T17:03:21Z) - SPEC: Summary Preference Decomposition for Low-Resource Abstractive
Summarization [21.037841262371355]
We present a framework to transfer few-shot learning processes from source corpora to the target corpus.
Our methods achieve state-of-the-art performance on six diverse corpora with 30.11%/33.95%/27.51% and 26.74%/31.14%/24.48% average improvements on ROUGE-1/2/L under 10- and 100-example settings.
arXiv Detail & Related papers (2023-03-24T14:07:03Z) - Recitation-Augmented Language Models [85.30591349383849]
We show that RECITE is a powerful paradigm for knowledge-intensive NLP tasks.
Specifically, we show that by utilizing recitation as the intermediate step, a recite-and-answer scheme can achieve new state-of-the-art performance.
arXiv Detail & Related papers (2022-10-04T00:49:20Z) - Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting.
Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking.
We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
arXiv Detail & Related papers (2020-10-24T11:55:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.