RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Jailbreak attacks suppress Adversarially Compromised Heads in early layers but leave Safety-Aligned Heads active in mid-layers, producing robust harmful features usable for competitive training-free detection.
citing papers explorer
-
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
-
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
Jailbreak attacks suppress Adversarially Compromised Heads in early layers but leave Safety-Aligned Heads active in mid-layers, producing robust harmful features usable for competitive training-free detection.