Pith. sign in

REVIEW 2 cited by

Transformer-based Causal Language Models Perform Clustering

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 2402.12151 v2 pith:FNEZ2XGC submitted 2024-02-19 cs.CL cs.AI

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

Even though large language models (LLMs) have demonstrated remarkable capability in solving various natural language tasks, the capability of an LLM to follow human instructions is still a concern. Recent works have shown great improvements in the instruction-following capability via additional training for instruction-following tasks. However, the mechanisms responsible for effective instruction-following capabilities remain inadequately understood. Here, we introduce a simplified instruction-following task and use synthetic datasets to analyze a Transformer-based causal language model. Our findings suggest that the model learns task-specific information by clustering data within its hidden space, with this clustering process evolving dynamically during learning. We also demonstrate how this phenomenon assists the model in handling unseen instances, and validate our results in a more realistic setting. Furthermore, we present inspired applications regarding pre-training and alignment.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Attention's forward pass and Frank-Wolfe

    math.OC 2025-08 conditional novelty 6.0 of 10

    Hardmax self-attention is shown to be a Frank-Wolfe iteration; with positive-definite key-query it converges to Voronoi-cell vertices, and a Markov-chain version of soft attention is metastable there for exponential-i...

  2. Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs

    cs.LG 2025-08 unverdicted novelty 4.0 of 10

    A submission whose abstract describes a new graph neural operator for PDEs but whose full text is a different paper, leaving the claimed method and results unverifiable.

Pith tools