Pith. sign in

REVIEW 4 cited by

SelfIE: Self-Interpretation of Large Language Model Embeddings

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 2403.10949 v2 pith:BE4FQTHF submitted 2024-03-16 cs.CL cs.AIcs.LG

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

How do large language models (LLMs) obtain their answers? The ability to explain and control an LLM's reasoning process is key for reliability, transparency, and future model developments. We propose SelfIE (Self-Interpretation of Embeddings), a framework that enables LLMs to interpret their own embeddings in natural language by leveraging their ability to respond to inquiries about a given passage. Capable of interpreting open-world concepts in the hidden embeddings, SelfIE reveals LLM internal reasoning in cases such as making ethical decisions, internalizing prompt injection, and recalling harmful knowledge. SelfIE's text descriptions on hidden embeddings also open up new avenues to control LLM reasoning. We propose Supervised Control, which allows editing open-ended concepts while only requiring gradient computation of individual layer. We extend RLHF to hidden embeddings and propose Reinforcement Control that erases harmful knowledge in LLM without supervision targets.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Verbalizable Representations Form a Global Workspace in Language Models

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Language models represent their current reasoning in a small, readable set of verbalizable vectors (the J-space) that functions like a global workspace.

  2. Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

    cs.CL 2025-05 conditional novelty 7.0 of 10

    Alignment on Llama 3 reduces explicit bias but amplifies implicit bias, because aligned models no longer represent 'black' and 'white' as racial concepts in ambiguous contexts.

  3. InverseScope: Scalable Activation Inversion for Interpreting Large Language Models

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A new conditional-generation architecture plus a feature-consistency metric make activation inversion practical for LLMs up to 7B parameters, with experiments on IOI, RAVEL, and in-context learning.

  4. Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models

    cs.CL 2025-06 reject novelty 3.0 of 10

    A survey of LLM hallucination research that formalizes hallucination types and argues, via incompleteness and undecidability arguments, that hallucinations cannot be fully eliminated.

Pith tools