Pith. sign in

REVIEW 1 cited by

Representations Matter: Embedding Modes of Large Language Models using Dynamic Mode Decomposition

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 2309.01245 v1 pith:UR7D5AYJ submitted 2023-09-03 cs.CL cs.AI

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

Existing large language models (LLMs) are known for generating "hallucinated" content, namely a fabricated text of plausibly looking, yet unfounded, facts. To identify when these hallucination scenarios occur, we examine the properties of the generated text in the embedding space. Specifically, we draw inspiration from the dynamic mode decomposition (DMD) tool in analyzing the pattern evolution of text embeddings across sentences. We empirically demonstrate how the spectrum of sentence embeddings over paragraphs is constantly low-rank for the generated text, unlike that of the ground-truth text. Importantly, we find that evaluation cases having LLM hallucinations correspond to ground-truth embedding patterns with a higher number of modes being poorly approximated by the few modes associated with LLM embedding patterns. In analogy to near-field electromagnetic evanescent waves, the embedding DMD eigenmodes of the generated text with hallucinations vanishes quickly across sentences as opposed to those of the ground-truth text. This suggests that the hallucinations result from both the generation techniques and the underlying representation.

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. TS-RAG: Retrieval Augmented Generation for Time Series Forecasting

    cs.AI 2026-08 conditional novelty 4.0 of 10

    A retrieval-augmented transformer with learned reference tokens shows marginal average MSE improvement over strong baselines on six time series benchmarks.

Pith tools