SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.17519 · 2024

Entropy-Based Decoding for Retrieval-Augmented Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and internal knowledge sources. In this paper, we introduce a novel, training-free decoding method guided by entropy considerations to mitigate this issue. Our approach utilizes entropy-based document-parallel ensemble decoding to prioritize low-entropy distributions from retrieved documents, thereby enhancing the extraction of relevant information of context. Additionally, it incorporates a contrastive decoding mechanism that contrasts the obtained low-entropy ensemble distribution with the high-entropy distribution derived from the model's internal knowledge across layers, which ensures a greater emphasis on reliable external information. Extensive experiments on open-domain question answering datasets demonstrate the superiority of our method.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.17519")
get_code_for_paper("2406.17519")
have("2406.17519")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.17519.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.17519.svg)](https://syntology.ai/paper/2406.17519)

Connect an agent — have() is free.