Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering

TL;DR

This paper introduces KnowPAT, a novel alignment method that enhances large language models for domain-specific question answering by aligning model preferences with human expectations, improving real-world application performance.

Contribution

The paper proposes a new preference alignment approach, KnowPAT, which constructs preference sets and a unified alignment objective to better tailor LLM responses to human and domain-specific needs.

Findings

KnowPAT outperforms 15 baseline methods in domain-specific QA tasks.

It effectively aligns LLM preferences with human expectations.

Experiments demonstrate improved accuracy and user satisfaction.

Abstract

Deploying large language models (LLMs) to real scenarios for domain-specific question answering (QA) is a key thrust for LLM applications, which poses numerous challenges, especially in ensuring that responses are both accommodating to user requirements and appropriately leveraging domain-specific knowledge bases. They are the two major difficulties for LLM application as vanilla fine-tuning falls short of addressing. Combining these requirements, we conceive of them as the requirement for the model's preference to be harmoniously aligned with humans'. Thus, we introduce Knowledgeable Preference AlignmenT (KnowPAT), which constructs two kinds of preference sets to tackle the two issues. Besides, we design a new alignment objective to align the LLM preference with different human preferences uniformly, aiming to optimize LLM performance in real-world, domain-specific QA settings. Adequate experiments and comprehensive comparisons with 15 baseline methods illustrate that our KnowPAT is a superior pipeline for real-scenario domain-specific QA with LLMs.