concept
active
concept:explicit-esr

Explicit ESR

The form of ESR focused on in this paper, measured by verbal self-interruption phrases as segment boundaries

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • Implicit ESR
    related_to
    Form of ESR occurring without explicit verbal self-interruption markers, not captured by current metrics
  • Endogenous Steering Resistance
    extends
    The central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Can ESR be adversarially circumvented?question0.735
    Open security question about robustness of ESR-based defenses
  • Meta-Prompting for ESR Enhancementmethod0.734
    Appending instructional meta-prompts to object-level prompts to deliberately enhance ESR in models
  • Scale-Dependent ESRconcept0.732
    The observed pattern that ESR appears predominantly in the largest model tested, suggesting scale-dependence
  • Does ESR reflect model scale, architecture, or training procedures?question0.726
    Central unresolved question about the mechanism behind ESR's apparent size-dependence
  • ESR Rate (metric)concept0.725
    Primary metric: percentage of responses containing multiple attempts that successfully improve on the first attempt
  • ESR Testing Pipelinemethod0.719
    Three-step protocol: (1) object-level prompting, (2) SAE-latent steering, (3) judge model scoring of attempts
  • SFR-DeepResearchframework0.711
    The paper's core contribution: an RL-based framework for training autonomous single-agent LLMs to perform deep research with web search, browsing, and code execution.
  • SimCLRmethod0.684
    Self-supervised contrastive learning method cited as instance of NCE-type objectives that converge to PMI kernel