Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
- URL: http://arxiv.org/abs/2406.11514v1
- Date: Mon, 17 Jun 2024 13:21:23 GMT
- Title: Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
- Authors: Yi Fang, Moxin Li, Wenjie Wang, Hui Lin, Fuli Feng,
- Abstract summary: Large Language Models (LLMs) excel in various natural language processing tasks but struggle with hallucination issues.
We propose a CounterFactual Multi-Agent Debate (CFMAD) framework to override LLMs' inherent biases for answer inspection.
- Score: 45.38821594541265
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) excel in various natural language processing tasks but struggle with hallucination issues. Existing solutions have considered utilizing LLMs' inherent reasoning abilities to alleviate hallucination, such as self-correction and diverse sampling methods. However, these methods often overtrust LLMs' initial answers due to inherent biases. The key to alleviating this issue lies in overriding LLMs' inherent biases for answer inspection. To this end, we propose a CounterFactual Multi-Agent Debate (CFMAD) framework. CFMAD presets the stances of LLMs to override their inherent biases by compelling LLMs to generate justifications for a predetermined answer's correctness. The LLMs with different predetermined stances are engaged with a skeptical critic for counterfactual debate on the rationality of generated justifications. Finally, the debate process is evaluated by a third-party judge to determine the final answer. Extensive experiments on four datasets of three tasks demonstrate the superiority of CFMAD over existing methods.
Related papers
- Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models [70.19081534515371]
Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks.
They generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences.
We propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers.
arXiv Detail & Related papers (2024-07-04T18:47:42Z) - A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation [72.93327642336078]
We propose Belief Tree Propagation (BTProp), a probabilistic framework for hallucination detection.
BTProp introduces a belief tree of logically related statements by decomposing a parent statement into child statements.
Our method improves baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.
arXiv Detail & Related papers (2024-06-11T05:21:37Z) - Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection [90.71323430635593]
We propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers.
It thoroughly compares the trustability of multiple candidate answers to mitigate the over-trust in LLM-generated incorrect answers.
This framework can be seamlessly integrated with existing approaches for superior self-detection.
arXiv Detail & Related papers (2024-03-15T02:38:26Z) - Measuring and Reducing LLM Hallucination without Gold-Standard Answers [25.274254957260904]
hallucination generates factually incorrect yet seemingly convincing answers.
Existing hallucination metrics require having a benchmark dataset with gold-standard answers.
FEWL is specifically designed for the scenario when gold-standard answers are absent.
arXiv Detail & Related papers (2024-02-16T02:32:06Z) - The ART of LLM Refinement: Ask, Refine, and Trust [85.75059530612882]
We propose a reasoning with refinement objective called ART: Ask, Refine, and Trust.
It asks necessary questions to decide when an LLM should refine its output.
It achieves a performance gain of +5 points over self-refinement baselines.
arXiv Detail & Related papers (2023-11-14T07:26:32Z) - Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate [85.89346248535922]
We propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
Our framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation.
arXiv Detail & Related papers (2023-05-30T15:25:45Z) - Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via
Debate [19.887103433032774]
Large language models (LLMs) have shown impressive performance in complex reasoning tasks.
This work explores testing LLMs' reasoning by engaging with them in a debate-like conversation.
We find that despite their impressive performance, LLMs like ChatGPT cannot maintain their beliefs in truth for a significant portion of examples.
arXiv Detail & Related papers (2023-05-22T15:47:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.