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

• URL: http://arxiv.org/abs/2309.04858v1
• Date: Sat, 9 Sep 2023 18:19:47 GMT
• Title: Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
• Authors: Daphne Ippolito, Nicholas Carlini, Katherine Lee, Milad Nasr, Yun William Yu
• Abstract summary: We present methods to reverse-engineer the decoding method used to generate text. Our ability to discover which decoding strategy was used has implications for detecting generated text.
• Score: 73.52878118434147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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).

Related papers

• Remote Timing Attacks on Efficient Language Model Inference [63.79839291641793]
  We show it is possible to exploit timing differences to mount a timing attack. We show how it is possible to learn the topic of a user's conversation with 90%+ precision. An adversary can leverage a boosting attack to recover PII placed in messages for open source systems.
  arXiv  Detail & Related papers  (2024-10-22T16:51:36Z)
• Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation [16.49758711633611]
  Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. In this work, we explore the use of Prompt Tuning to achieve controlled language generation. We demonstrate the efficacy of our method towards mitigating harmful, toxic, and biased text generated by language models.
  arXiv  Detail & Related papers  (2024-04-08T01:54:28Z)
• Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text [1.9185059111021852]
  We investigate how pre-trained Language Models handle code-switched text in three dimensions. Our findings reveal that pre-trained language models are effective in generalising to code-switched text.
  arXiv  Detail & Related papers  (2024-03-07T19:46:03Z)
• Momentum Decoding: Open-ended Text Generation As Graph Exploration [49.812280360794894]
  Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. We formulate open-ended text generation from a new perspective, i.e., we view it as an exploration process within a directed graph. We propose a novel decoding method -- textitmomentum decoding -- which encourages the LM to explore new nodes outside the current graph.
  arXiv  Detail & Related papers  (2022-12-05T11:16:47Z)
• A Simple, Yet Effective Approach to Finding Biases in Code Generation [16.094062131137722]
  This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones. We propose the "block of influence" concept, which enables a modular decomposition and analysis of the coding challenges.
  arXiv  Detail & Related papers  (2022-10-31T15:06:15Z)
• Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages [86.08359401867577]
  Back-translation is widely known for its effectiveness for neural machine translation when little to no parallel data is available. We propose performing back-translation via code summarization and generation. We show that our proposed approach performs competitively with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-23T08:20:41Z)
• Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
  We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models. Our method does not assume the vocabulary, tokenization or even generation order is shared.
  arXiv  Detail & Related papers  (2022-05-19T01:27:53Z)
• On Decoding Strategies for Neural Text Generators [73.48162198041884]
  We study the interaction between language generation tasks and decoding strategies. We measure changes in attributes of generated text as a function of both decoding strategy and task. Our results reveal both previously-observed and surprising findings.
  arXiv  Detail & Related papers  (2022-03-29T16:25:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.