BOUND refines LLMs' package-validity boundary via targeted editing to cut package hallucination rates by 79.9% on edit prompts and 65.4% on unseen prompts in recommendation tasks while generalizing to code generation.
Matthew Sotoudeh and A Thakur
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Parameter-based knowledge editing in LLMs induces reasoning collapse via dimensional collapse and is consistently outperformed by a retrieval baseline across varied edit counts, knowledge complexity, and evaluation metrics.
Neural model editing is cast as RL in MaskWorld and ShiftWorld environments, with learned policies reaching near-zero forget accuracy while retaining over 90% on retain sets for unlearning and improving bias metrics by over 5%.
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.
citing papers explorer
-
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
Parameter-based knowledge editing in LLMs induces reasoning collapse via dimensional collapse and is consistently outperformed by a retrieval baseline across varied edit counts, knowledge complexity, and evaluation metrics.