Bring Your Own Data! Self-Sensitivity Evaluation for Large Language Models
Research Area: Evaluation
Keywords: Evaluations
TL;DR: Proposes a novel evaluation framework for LLMs using invariances/sensitivities
Abstract: With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that the model will not respond to client requests with profanity. Current evaluations approach this problem using small, domain-specific datasets with human-curated labels. These evaluation sets are often sampled from a narrow and simplified distribution, and data sources can unknowingly be leaked into the training set. To alleviate these issues in traditional evaluation, we propose a complementary framework for additional self-sensitivity evaluation of LLMs by analyzing their sensitivity or invariance to transformations on the input text. Self-sensitivity evaluation can directly monitor LLM behavior on datasets collected in-the-wild or streamed during live model deployment. We demonstrate self-sensitivity evaluation strategies for measuring closed-book knowledge, toxicity, long-range context dependence, in addition to sensitivity to grammatical structure and tokenization errors. When comparisons to similar human-labeled benchmarks are available, we find strong correlations between self-sensitivity and human-supervised evaluations. The self-sensitivity paradigm complements current evaluation strategies that rely on labeled data.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 1010
Loading