You've Changed: Detecting Modification of Black-Box Large Language Models

• URL: http://arxiv.org/abs/2504.12335v1
• Date: Mon, 14 Apr 2025 04:16:43 GMT
• Title: You've Changed: Detecting Modification of Black-Box Large Language Models
• Authors: Alden Dima, James Foulds, Shimei Pan, Philip Feldman,
• Abstract summary: Large Language Models (LLMs) are often provided as a service via an API, making it challenging for developers to detect changes in their behavior.<n>We present an approach to monitor LLMs for changes by comparing the distributions of linguistic and psycholinguistic features of generated text.
• Score: 4.7541096609711
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are often provided as a service via an API, making it challenging for developers to detect changes in their behavior. We present an approach to monitor LLMs for changes by comparing the distributions of linguistic and psycholinguistic features of generated text. Our method uses a statistical test to determine whether the distributions of features from two samples of text are equivalent, allowing developers to identify when an LLM has changed. We demonstrate the effectiveness of our approach using five OpenAI completion models and Meta's Llama 3 70B chat model. Our results show that simple text features coupled with a statistical test can distinguish between language models. We also explore the use of our approach to detect prompt injection attacks. Our work enables frequent LLM change monitoring and avoids computationally expensive benchmark evaluations.

Related papers

• Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding [71.01099784480597]
  Large language models (LLMs) excel at a range of tasks through in-context learning (ICL) We introduce In-Context Contrastive Decoding (ICCD), a novel method that emphasizes input-label mapping. ICCD emphasizes input-label mapping by contrasting the output distributions between positive and negative in-context examples.
  arXiv  Detail & Related papers  (2025-02-19T14:04:46Z)
• Predicting the Performance of Black-box LLMs through Self-Queries [60.87193950962585]
  Large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial.<n>In this paper, we extract features of LLMs in a black-box manner by using follow-up prompts and taking the probabilities of different responses as representations.<n>We demonstrate that training a linear model on these low-dimensional representations produces reliable predictors of model performance at the instance level.
  arXiv  Detail & Related papers  (2025-01-02T22:26:54Z)
• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method [108.56493934296687]
  We introduce a divergence-based calibration method, inspired by the divergence-from-randomness concept, to calibrate token probabilities for pretraining data detection.<n>We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
  arXiv  Detail & Related papers  (2024-09-23T07:55:35Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code? [51.29970742152668]
  We highlight relying on accuracy-based measurements may lead to an overestimation of models' capabilities. To address these issues, we introduce a technique called SyntaxEval in Syntactic Capabilities.
  arXiv  Detail & Related papers  (2024-01-03T02:44:02Z)
• Measuring Distributional Shifts in Text: The Advantage of Language Model-Based Embeddings [11.393822909537796]
  An essential part of monitoring machine learning models in production is measuring input and output data drift. Recent advancements in large language models (LLMs) indicate their effectiveness in capturing semantic relationships. We propose a clustering-based algorithm for measuring distributional shifts in text data by exploiting such embeddings.
  arXiv  Detail & Related papers  (2023-12-04T20:46:48Z)
• Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting [68.19544657508509]
  Large language models (LLMs) are adopted as a fundamental component of language technologies. We find that several widely used open-source LLMs are extremely sensitive to subtle changes in prompt format in few-shot settings. We propose an algorithm that rapidly evaluates a sampled set of plausible prompt formats for a given task, and reports the interval of expected performance without accessing model weights.
  arXiv  Detail & Related papers  (2023-10-17T15:03:30Z)
• Masked Language Model Based Textual Adversarial Example Detection [14.734863175424797]
  Adrial attacks are a serious threat to reliable deployment of machine learning models in safety-critical applications. We propose a novel textual adversarial example detection method, namely Masked Model-based Detection (MLMD)
  arXiv  Detail & Related papers  (2023-04-18T06:52:14Z)
• Interpretable Unified Language Checking [42.816372695828306]
  We present an interpretable, unified, language checking (UniLC) method for both human and machine-generated language. We find that LLMs can achieve high performance on a combination of fact-checking, stereotype detection, and hate speech detection tasks.
  arXiv  Detail & Related papers  (2023-04-07T16:47:49Z)

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.