Pith. sign in

REVIEW 2 cited by

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router

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 2410.02684 v1 pith:H7PBCME3 submitted 2024-10-03 cs.CL

classification cs.CL
keywords harmfulinformationcontentfine-grainedhiddenguardllmsresponseswhile
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or sensitive information. However, current alignment approaches, which rely heavily on refusal strategies, such as training models to completely reject harmful prompts or applying coarse filters are limited by their binary nature. These methods either fully deny access to information or grant it without sufficient nuance, leading to overly cautious responses or failures to detect subtle harmful content. For example, LLMs may refuse to provide basic, public information about medication due to misuse concerns. Moreover, these refusal-based methods struggle to handle mixed-content scenarios and lack the ability to adapt to context-dependent sensitivities, which can result in over-censorship of benign content. To overcome these challenges, we introduce HiddenGuard, a novel framework for fine-grained, safe generation in LLMs. HiddenGuard incorporates Prism (rePresentation Router for In-Stream Moderation), which operates alongside the LLM to enable real-time, token-level detection and redaction of harmful content by leveraging intermediate hidden states. This fine-grained approach allows for more nuanced, context-aware moderation, enabling the model to generate informative responses while selectively redacting or replacing sensitive information, rather than outright refusal. We also contribute a comprehensive dataset with token-level fine-grained annotations of potentially harmful information across diverse contexts. Our experiments demonstrate that HiddenGuard achieves over 90% in F1 score for detecting and redacting harmful content while preserving the overall utility and informativeness of the model's responses.

Discussion (0). Continue with ORCID 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. V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Video LLMs understand harmful content but activate weaker refusal signals when the query is benign; prompt realignment reduces attack success from ~48% to ~1%.

  2. Large Language Models as Computable Approximations to Solomonoff Induction

    cs.LG 2025-05 reject novelty 2.0 of 10

    The paper argues LLMs are computable approximations of Solomonoff induction, but its central derivation recovers the model's own probabilities by construction.

Pith tools