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

arXiv: https://arxiv.org/abs/2110.07280 · HTML: https://mlsanity.com/paper/2110.07280/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://mlsanity.com/paper/1804.06059/) (2018)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [Commonsense Knowledge Mining from Pretrained Models](https://mlsanity.com/paper/1909.00505/) (2019)
- [Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases](https://mlsanity.com/paper/2106.09231/) (2021)
- [E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT](https://mlsanity.com/paper/1911.03681/) (2019)
- [BERTese: Learning to Speak to BERT](https://mlsanity.com/paper/2103.05327/) (2021)
- [Robust Encodings: A Framework for Combating Adversarial Typos](https://mlsanity.com/paper/2005.01229/) (2020)
- [Training verified learners with learned verifiers](https://mlsanity.com/paper/1805.10265/) (2018)
- [Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality](https://mlsanity.com/paper/2106.04102/) (2021)
- [Static Embeddings as Efficient Knowledge Bases?](https://mlsanity.com/paper/2104.07094/) (2021)

## Built on by (most cited first, 22 of 22)

- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [Measuring Reliability of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2211.05853/) (2022)
- [Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs](https://mlsanity.com/paper/2305.14279/) (2023)
- [Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models](https://mlsanity.com/paper/2310.16570/) (2023)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)
- [BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models](https://mlsanity.com/paper/2206.14268/) (2022)
- [Factual Consistency of Multilingual Pretrained Language Models](https://mlsanity.com/paper/2203.11552/) (2022)
- [Semantic Consistency for Assuring Reliability of Large Language Models](https://mlsanity.com/paper/2308.09138/) (2023)
- [Understanding Finetuning for Factual Knowledge Extraction from Language Models](https://mlsanity.com/paper/2301.11293/) (2023)
- [Improving Consistency in Large Language Models through Chain of Guidance](https://mlsanity.com/paper/2502.15924/) (2025)
- [One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER](https://mlsanity.com/paper/2301.10410/) (2023)
- [MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)](https://mlsanity.com/paper/2410.04778/) (2024)
- [Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction](https://mlsanity.com/paper/2404.12957/) (2024)
- [SPE: Symmetrical Prompt Enhancement for Fact Probing](https://mlsanity.com/paper/2211.07078/) (2022)
- [Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models](https://mlsanity.com/paper/2305.14775/) (2023)
- [PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2210.13715/) (2022)
- [Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models](https://mlsanity.com/paper/2408.14595/) (2024)
- [Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models](https://mlsanity.com/paper/2310.11085/) (2023)
- [UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing](https://mlsanity.com/paper/2404.01253/) (2024)
- [CoRA: Optimizing Low-Rank Adaptation with Common Subspace of Large Language Models](https://mlsanity.com/paper/2409.02119/) (2024)
- [Enhancing Fact Retrieval in PLMs through Truthfulness](https://mlsanity.com/paper/2410.13562/) (2024)

## Abstract (arXiv)

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 P-Adapters successful and conclude that a significant factor is access to the LLM's embeddings of the original natural language prompt, particularly the subject of the entity pair being queried.