FIELD NOTES TOPIC
long-context reasoning
3 notes, newest first.
Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning
Researchers introduce Group-Calibrated On-Policy Distillation (GC-OPD), a method for long-context reasoning tasks that aims to address the mismatch between on-policy distillation and task-specific verifiers. The new…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Researchers have proposed a new method called Recursive Evidence Replay (RECONTEXT) to improve the ability of large language models to understand and reason over long contexts. This method doesn't require training…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Researchers propose a new method called Recursive Evidence Replay (RECONTEXT) to improve the ability of large language models (LLMs) to understand and reason over long contexts. This method doesn't require training and…
