Year: 2026
Type: conference-paper
Abstract: Although large language models (LLMs) excel at factual recall, they can still propagate stale or incorrect knowledge, making in-context knowledge editing a gradient-free remedy suitable for black-box APIs.These knowledge editors that use in-context learning typically rely on a single retriever and surface-similarity heuristics to build prompts.However, a key observation in this study is that retrievers can be complementary: semantic rankers may recover paraphrased evidence, while lexical or feature-based retrievers may preserve precise entities and cues.This creates two gaps in single-retriever editors: they (i) miss complementary evidence that different retrievers surface and (ii) cannot adapt when one retriever is clearly more reliable for a query.We introduce a Feature-Weighted Ensemble for In-context Knowledge Editing (FWE-IKE) that calibrates three heterogeneous rankers (LLM-, BERT-, and MLP-based), extracts simple confidence features from each ranker, predicts per-query mixture weights, and applies a conservative margin-based routing gate that selects a single expert when confident; otherwise we mix calibrated distributions with learned per-query weights.On the COUNTER-FACT benchmark, FWE-IKE attains 88.33% Edit-Success Rate, a +3.0 point gain over the best single retriever and approaching the oracle upper bound (91%).Case studies, an ablation study, and analyses show the method systematically recovers complementary wins (e.g., BERT-only, LLM-only, MLPonly slices).FWE-IKE improves edit accuracy without touching model weights and provides a practical path to more robust, confidenceaware retrieval for IKE.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: National Science Foundation
OpenAlex ID: W7166828673