Pith. sign in

REVIEW 1 cited by

How Well Do Large Language Models Truly Ground?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.09069 v2 pith:XEHDTZMZ submitted 2023-11-15 cs.CL cs.AI

classification cs.CLcs.AI
keywords groundingmodelsdefinitionknowledgelanguagelargellmsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

To reduce issues like hallucinations and lack of control in Large Language Models (LLMs), a common method is to generate responses by grounding on external contexts given as input, known as knowledge-augmented models. However, previous research often narrowly defines "grounding" as just having the correct answer, which does not ensure the reliability of the entire response. To overcome this, we propose a stricter definition of grounding: a model is truly grounded if it (1) fully utilizes the necessary knowledge from the provided context, and (2) stays within the limits of that knowledge. We introduce a new dataset and a grounding metric to evaluate model capability under the definition. We perform experiments across 25 LLMs of different sizes and training methods and provide insights into factors that influence grounding performance. Our findings contribute to a better understanding of how to improve grounding capabilities and suggest an area of improvement toward more reliable and controllable LLM applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI

    cs.LG 2024-12 conditional novelty 5.0 of 10

    DSAI extracts interpretable latent features from text through five LLM stages and ranks them by a prominence score that measures how well each rule separates positive from negative examples.

Pith tools