Estimating Knowledge in Large Language Models Without Generating a Single Token

• URL: http://arxiv.org/abs/2406.12673v2
• Date: Tue, 29 Oct 2024 08:40:25 GMT
• Title: Estimating Knowledge in Large Language Models Without Generating a Single Token
• Authors: Daniela Gottesman, Mor Geva,
• Abstract summary: Current methods to evaluate knowledge in large language models (LLMs) query the model and then evaluate its generated responses. In this work, we ask whether evaluation can be done before the model has generated any text. Experiments with a variety of LLMs show that KEEN, a simple probe trained over internal subject representations, succeeds at both tasks.
• Score: 12.913172023910203
• License:
• Abstract: To evaluate knowledge in large language models (LLMs), current methods query the model and then evaluate its generated responses. In this work, we ask whether evaluation can be done before the model has generated any text. Concretely, is it possible to estimate how knowledgeable a model is about a certain entity, only from its internal computation? We study this question with two tasks: given a subject entity, the goal is to predict (a) the ability of the model to answer common questions about the entity, and (b) the factuality of open-ended responses generated by the model about the entity. Experiments with a variety of LLMs show that KEEN, a simple probe trained over internal subject representations, succeeds at both tasks - correlating with both the QA accuracy of the model per-subject and FActScore, a recent factuality metric in open-ended generation. Moreover, KEEN naturally aligns with the model's hedging behavior and faithfully reflects changes in the model's knowledge after fine-tuning. Lastly, we show a more interpretable yet equally performant variant of KEEN, which highlights a small set of tokens indicative of clusters and gaps in the model's knowledge. Being simple and lightweight, KEEN can be leveraged to guide decisions such as when it is appropriate to apply further training or augment queries with retrieval.

Related papers

• OLMES: A Standard for Language Model Evaluations [64.85905119836818]
  We propose OLMES, a practical, open standard for reproducible language model evaluations. We identify and review the varying factors in evaluation practices adopted by the community. OLMES supports meaningful comparisons between smaller base models that require the unnatural "cloze" formulation of multiple-choice questions.
  arXiv  Detail & Related papers  (2024-06-12T17:37:09Z)
• Can I understand what I create? Self-Knowledge Evaluation of Large Language Models [31.85129258347539]
  Large language models (LLMs) have achieved remarkable progress in linguistic tasks. Inspired by Feynman's principle of understanding through creation, we introduce a self-knowledge evaluation framework.
  arXiv  Detail & Related papers  (2024-06-10T09:53:54Z)
• Context versus Prior Knowledge in Language Models [49.17879668110546]
  Language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We propose two mutual information-based metrics to measure a model's dependency on a context and on its prior about an entity.
  arXiv  Detail & Related papers  (2024-04-06T13:46:53Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering [26.34649731975005]
  Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for question answering (QA) While the model responses tend to be natural and fluent, the additional verbosity makes traditional QA evaluation metrics unreliable for accurately quantifying model performance. We use both automatic and human evaluation to evaluate these models along two dimensions: 1) how well they satisfy the user's information need (correctness) and 2) whether they produce a response based on the provided knowledge (faithfulness)
  arXiv  Detail & Related papers  (2023-07-31T17:41:00Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [50.62245481416744]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world. We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique. By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Evaluating Representations with Readout Model Switching [19.907607374144167]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)

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.