Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness
We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model by estimating a numeric confidence score for any output it generated. Our uncertainty quantification technique works for any LLM accessible only via a black-box API, whose training data remains unknown. By expending a bit of extra computation, users of any LLM API can now get the same response as they would ordinarily, as well as a confidence estimate that cautions when not to trust this response. Experiments on both closed and open-form Question-Answer benchmarks reveal that BSDetector more accurately identifies incorrect LLM responses than alternative uncertainty estimation procedures (for both GPT-3 and ChatGPT). By sampling multiple responses from the LLM and considering the one with the highest confidence score, we can additionally obtain more accurate responses from the same LLM, without any extra training steps. In applications involving automated evaluation with LLMs, accounting for our confidence scores leads to more reliable evaluation in both human-in-the-loop and fully-automated settings (across both GPT 3.5 and 4).
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelUncertainty QuantificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where their pre-trained knowledge is insuffici…
Information RetrievalQuestion AnsweringRAGRetrieval+2Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores
Large language models (LLMs) are stochastic, and not all models give deterministic answers, even when setting temperature to zero with a fixed random seed. However, few benchmark studies attempt to quantify uncertainty, …
On the Role of Unobserved Sequences on Sample-based Uncertainty Quantification for LLMs
Quantifying uncertainty in large language models (LLMs) is important for safety-critical applications because it helps spot incorrect answers, known as hallucinations. One major trend of uncertainty quantification method…
Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
Large language models (LLMs) have shown strong capabilities, enabling concise, context-aware answers in question answering (QA) tasks. The lack of transparency in complex LLMs has inspired extensive research aimed at dev…
Question AnsweringImproving Uncertainty Quantification in Large Language Models via Semantic Embeddings
Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in …
Question AnsweringUncertainty Quantification