Tag

knowledge vector

1 views collected around this technical thread.

JD Tech Talk
JD Tech Talk
Jul 16, 2024 · Artificial Intelligence

Task‑Aware Decoding (TaD): A Plug‑and‑Play Method to Mitigate Hallucinations in Large Language Models

TaD, a task‑aware decoding technique jointly developed by JD.com and Tsinghua University and presented at IJCAI 2024, leverages differences between pre‑ and post‑fine‑tuned LLM outputs to construct knowledge vectors, significantly reducing hallucinations across various models, tasks, and data‑scarce scenarios, especially when combined with RAG.

AILLMRAG
0 likes · 18 min read
Task‑Aware Decoding (TaD): A Plug‑and‑Play Method to Mitigate Hallucinations in Large Language Models