SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.04858 · 2023

Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System

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

Neural language models are increasingly deployed into APIs and websites that allow a user to pass in a prompt and receive generated text. Many of these systems do not reveal generation parameters. In this paper, we present methods to reverse-engineer the decoding method used to generate text (i.e., top-$k$ or nucleus sampling). Our ability to discover which decoding strategy was used has implications for detecting generated text. Additionally, the process of discovering the decoding strategy can reveal biases caused by selecting decoding settings which severely truncate a model's predicted distributions. We perform our attack on several families of open-source language models, as well as on production systems (e.g., ChatGPT).

For agents

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

get_harvested_code_for_paper("2309.04858")
get_code_for_paper("2309.04858")
have("2309.04858")

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

curl https://syntology.ai/api/ran/2309.04858.json

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

[![Syntology run record](https://syntology.ai/api/ran/2309.04858.svg)](https://syntology.ai/paper/2309.04858)

Connect an agent — have() is free.