framework
active
framework:long-short-term-memory-lstm

Long Short-Term Memory (LSTM)

Recurrent neural network architecture used alongside GRUs in numeric task experiments; MAS applied to concatenated h and c vectors.

Neighborhood — ranked by edge-count

Papers (1)

paper

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.

  • Medium-term memoryconcept0.756
    Vascular clamp's function: holding specific predictions stable over timescales longer than working memory.
  • LM Intentionconcept0.749
    Operationalised as an LM adapting its behaviour when certain outcomes are fixed, indicating those outcomes were intended.
  • LM Beliefconcept0.742
    Contentious concept operationalised behaviourally as consistent outputs of P or similar content when directly asked about P.
  • Challenge of maintaining coherent persona or content over longer generated texts
  • Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
  • LLM Meta-Cognitionconcept0.730
    The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
  • The capacity of Kimi K2.5 to evaluate its own internal emotional state when steered, used as a novel interpretability signal
  • Related capability where LLMs correct their own outputs, studied via linear representations.