arXiv Open Access 2024

Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A

K Roth Rushil Gupta Simon Halle Bang Liu
Lihat Sumber

Abstrak

Large language models struggle to synthesize disparate pieces of information into a coherent plan when approaching a complex procedural task. In this work, we introduce a novel formalism and structure for such procedural knowledge. Based on this formalism, we present a novel procedural knowledge dataset called LCStep, which we created from LangChain tutorials. To leverage this procedural knowledge to solve new tasks, we propose analogy-augmented generation (AAG), which draws inspiration from the human ability to assimilate past experiences to solve unfamiliar problems. AAG uses a custom procedure memory store to retrieve and adapt specialized domain knowledge to answer new procedural tasks. We demonstrate that AAG outperforms few-shot and RAG baselines on LCStep, RecipeNLG, and CHAMP datasets under a pairwise LLM-based evaluation, corroborated by human evaluation in the case of RecipeNLG.

Topik & Kata Kunci

Penulis (4)

K

K Roth

R

Rushil Gupta

S

Simon Halle

B

Bang Liu

Format Sitasi

Roth, K., Gupta, R., Halle, S., Liu, B. (2024). Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A. https://arxiv.org/abs/2409.01344

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓