Introduces route-specialized dual adapters that route prompts to either an edit adapter or a locality adapter, achieving highest accuracy on CF, ZSRE, and MQuAKE benchmarks for 7B/8B models.
Evaluating the Ripple Effects of Knowledge Editing in Language Models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
RAID is a reflective agent system that infers intent from single expert edits and propagates corrections across compositional knowledge bases through a three-step architecture.
Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.
citing papers explorer
-
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
Introduces route-specialized dual adapters that route prompts to either an edit adapter or a locality adapter, achieving highest accuracy on CF, ZSRE, and MQuAKE benchmarks for 7B/8B models.
-
Scaling Expert Feedback with Reflective Edit Propagation in Compositional Knowledge Bases
RAID is a reflective agent system that infers intent from single expert edits and propagates corrections across compositional knowledge bases through a three-step architecture.
-
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Multi-agent debate with tit-for-tat arguments and a judge LLM improves reasoning by preventing LLMs from locking into incorrect initial solutions.