OATML

Large language model (LLM) systems, such as ChatGPT or Gemini, can show impressive reasoning and question-answering capabilities but often ‘hallucinate’ false outputs and unsubstantiated answers. Answering unreliably or without the necessary information prevents adoption in diverse fields, with problems including fabrication of legal precedents or untrue facts in news articles and even posing a risk to human life in medical domains such as radiology. Encouraging truthfulness through supervision or reinforcement has only been partially successful. Researchers need a general method for detecting hallucinations in LLMs that works even with new and unseen questions to which humans might not know the answer. Here we develop new methods grounded in statistics, proposing entropy-based uncertainty estimators for LLMs to detect a subset of hallucinations—confabulations—which are arbitrary and incorrect generations. Our method addresses the fact that one idea can be expressed in many ways by... [full abstract]

We introduce a method to measure uncertainty in large language models. For tasks like question answering, it is essential to know when we can trust the natural language outputs of foundation models. We show that measuring uncertainty in natural language is challenging because of "semantic equivalence" -- different sentences can mean the same thing. To overcome these challenges we introduce semantic entropy -- an entropy which incorporates linguistic invariances created by shared meanings. Our method is unsupervised, uses only a single model, and requires no modifications to off-the-shelf language models. In comprehensive ablation studies we show that the semantic entropy is more predictive of model accuracy on question answering data sets than comparable baselines.

Users often ask dialogue systems ambiguous questions that require clarification. We show that current language models rarely ask users to clarify ambiguous questions and instead provide incorrect answers. To address this, we introduce CLAM: a framework for getting language models to selectively ask for clarification about ambiguous user questions. In particular, we show that we can prompt language models to detect whether a given question is ambiguous, generate an appropriate clarifying question to ask the user, and give a final answer after receiving clarification. We also show that we can simulate users by providing language models with privileged information. This lets us automatically evaluate multi-turn clarification dialogues. Finally, CLAM significantly improves language models' accuracy on mixed ambiguous and unambiguous questions relative to SotA.

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically motivated measure of a network's simplicity which we call prunability: the smallest \emph{fraction} of the network's parameters that can be kept while pruning without adversely affecting its training loss. We show that this measure is highly predictive of a model's generalization performance across a large set of convolutional networks trained on CIFAR-10, does not grow with network size unlike existing pruning-based measures, and exhibits high correlation with test set loss even in a particularly challenging double descent setting. Lastly, we show that the success of prunability cannot be explained by its relation to known complexity measures based on models' margin, flatness of minima and optimization speed, finding that our new measure is similar to -... [full abstract]

OATML group members Sebastian Farquhar, Jannik Kossen and Yarin Gal, along with group alumni Lorenz Kuhn, published a study in Nature which introduces a breakthrough method for detecting hallucinations in LLMs using semantic entropy. You can read the paper here.

This is the code repository for the paper “Detecting hallucinations in large language models using semantic entropy”.

Can we detect confabulations, where LLMs invent plausible-sounding factoids? We show how, in research published at Nature. …

OATML group members and collaborators are proud to present 8 papers at NeurIPS 2022 main conference, and 11 workshop papers. …