# Analysis of Plan-based Retrieval for Grounded Text Generation

Source: [Analysis of Plan-based Retrieval for Grounded Text Generation](<https://www.sota2.com/research/paper/68fa74831e209131cea6218d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:08.755Z

Authors: Ameya Godbole, Nicholas Monath, Seungyeon Kim, Ankit Singh Rawat, Andrew McCallum, Manzil Zaheer

Published: 2024-08-20T02:19:35.000Z

## Abstract

In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametric knowledge (due to rarity, recency, domain, etc.). A common strategy to address this limitation is to infuse the language models with retrieval mechanisms, providing the model with relevant knowledge for the task. In this paper, we leverage the planning capabilities of instruction-tuned LLMs and analyze how planning can be used to guide retrieval to further reduce the frequency of hallucinations. We empirically evaluate several variations of our proposed approach on long-form text generation tasks. By improving the coverage of relevant facts, plan-guided retrieval and generation can produce more informative responses while providing a higher rate of attribution to source documents.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-hop Question Answering on HotpotQA l1](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-l1.md>): Multi-hop Question Answering; HotpotQA l1; Cost per Pass: 0.54.

- [Multi-hop Question Answering on MusiQue l3](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-l3.md>): Multi-hop Question Answering; MusiQue l3; Cost: 2.16.

- [Multi-hop Question Answering on Average (HotpotQA, 2WikiMultiHopQA, MusiQue) (Cost/Efficiency)](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-average-hotpotqa-2wikimultihopqa-musique-cost-efficiency.md>): Multi-hop Question Answering; HotpotQA, 2WikiMultiHopQA, and MusiQue Average all; Cost per Pass: 1.12.

- [Multi-hop Question Answering on 2WikiMultiHopQA l2](<https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-l2.md>): Multi-hop Question Answering; 2WikiMultiHopQA l2; Cost per Pass: 0.64.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2408.10490>)

[PDF](<https://arxiv.org/pdf/2408.10490.pdf>)