SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.18680 · 2024

Non-Linear Inference Time Intervention: Improving LLM Truthfulness

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

In this work, we explore LLM's internal representation space to identify attention heads that contain the most truthful and accurate information. We further developed the Inference Time Intervention (ITI) framework, which lets bias LLM without the need for fine-tuning. The improvement manifests in introducing a non-linear multi-token probing and multi-token intervention: Non-Linear ITI (NL-ITI), which significantly enhances performance on evaluation benchmarks. NL-ITI is tested on diverse multiple-choice datasets, including TruthfulQA, on which we report over 16% relative MC1 (accuracy of model pointing to the correct answer) improvement with respect to the baseline ITI results. Moreover, we achieved a 10% relative improvement over the recently released Truth Forest (TrFf) method that also focused on ITI improvement.

For agents

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

get_harvested_code_for_paper("2403.18680")
get_code_for_paper("2403.18680")
have("2403.18680")

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

curl https://syntology.ai/api/ran/2403.18680.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.18680.svg)](https://syntology.ai/paper/2403.18680)

Connect an agent — have() is free.