Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy

Zhihong Shao, Yeyun Gong, yelong shen, Minlie Huang, Nan Duan, Weizhu Chen

Submission Type: Regular Long Paper

Submission Track: Question Answering

Keywords: retrieval-augmented language model, prompting, retrieval

Abstract:

Retrieval-augmented generation has raise extensive attention as it is promising to address the limitations of large language models including outdated knowledge and hallucinations.
However, retrievers struggle to capture relevance, especially for queries with complex information needs.
Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to guide retrieval with generation.
In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner:
a model's response to a task input shows what might be needed to finish the task, and thus can serve as an informative context for retrieving more relevant knowledge which in turn helps generate a better response in another iteration.
Compared with recent work which interleaves retrieval with generation when completing a single output, Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints.
We evaluate Iter-RetGen on multi-hop question answering, fact verification, and commonsense reasoning, and show that it can flexibly leverage parametric knowledge and non-parametric knowledge, and is superior to or competitive with state-of-the-art retrieval-augmented baselines while causing fewer overheads of retrieval and generation.
We can further improve performance via generation-augmented retrieval adaptation.

Submission Number: 1433