P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts release_qyeqlkroivhh5offeunjvtnkyu

by Benjamin Newman, Prafulla Kumar Choubey, Nazneen Rajani

Released as a article .

2021  

Abstract

Recent work (e.g. LAMA (Petroni et al., 2019)) has found that the quality of the factual information extracted from Large Language Models (LLMs) depends on the prompts used to query them. This inconsistency is problematic because different users will query LLMs for the same information using different wording, but should receive the same, accurate responses regardless. In this work we aim to address this shortcoming by introducing P-Adapters: lightweight models that sit between the embedding layer and first attention layer of LLMs. They take LLM embeddings as input and output continuous prompts that are used to query the LLM. Additionally, we investigate Mixture of Experts (MoE) models that learn a set of continuous prompts ("experts") and select one to query the LLM. They require a separate classifier trained on human-annotated data to map natural language prompts to the continuous ones. P-Adapters perform comparably to the more complex MoE models in extracting factual information from BERT and RoBERTa while eliminating the need for additional annotations. P-Adapters show between 12-26% absolute improvement in precision and 36-50% absolute improvement in consistency over a baseline of only using natural language queries. Finally, we investigate what makes a P-adapter successful and conclude that access to the LLM's embeddings of the original natural language prompt, particularly the subject of the entity pair being asked about, is a significant factor.
In text/plain format

Archived Files and Locations

application/pdf  518.5 kB
file_xeynjp2a3ve2nedrrhx4yao5nq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-10-14
Version   v1
Language   en ?
arXiv  2110.07280v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 39a6beb4-2322-4899-b369-89a503cf30c1
API URL: JSON