Task-aware Decoding

JD Tech

Jul 22, 2024 · Artificial Intelligence

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

This article presents Task‑aware Decoding (TaD), a plug‑and‑play technique introduced by JD Tech and Tsinghua University and accepted at IJCAI 2024, which reduces intrinsic hallucinations in large language models by comparing pre‑ and post‑fine‑tuning outputs, and demonstrates its effectiveness combined with Retrieval‑Augmented Generation across various tasks.

Fine-tuningLLMRetrieval-Augmented Generation

0 likes · 18 min read

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

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