Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework (2406.03075v1)

Published 5 Jun 2024 in cs.CL

Abstract: The advent of LLMs has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often involve expensive and complex interventions during the training process. Moreover, some approaches emphasize problem disassembly while neglecting the crucial validation process, leading to performance degradation or limited applications. To overcome these limitations, we propose a Markov Chain-based multi-agent debate verification framework to enhance hallucination detection accuracy in concise claims. Our method integrates the fact-checking process, including claim detection, evidence retrieval, and multi-agent verification. In the verification stage, we deploy multiple agents through flexible Markov Chain-based debates to validate individual claims, ensuring meticulous verification outcomes. Experimental results across three generative tasks demonstrate that our approach achieves significant improvements over baselines.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Xiaoxi Sun (2 papers)
  2. Jinpeng Li (67 papers)
  3. Yan Zhong (24 papers)
  4. Dongyan Zhao (144 papers)
  5. Rui Yan (250 papers)
Citations (3)

Summary

We haven't generated a summary for this paper yet.