Abstract
This paper presents a way of enhancing the reliability of Large Multi-modal Models (LMMs) in addressing hallucination, where the models generate cross-modal inconsistent responses. Without additional training, we propose Counterfactual Inception, a novel method that implants counterfactual thinking into LMMs using self-generated counterfactual keywords. Our method is grounded in the concept of counterfactual thinking, a cognitive process where human considers alternative realities, enabling more extensive context exploration. Bridging the human cognition mechanism into LMMs, we aim for the models to engage with and generate responses that span a wider contextual scene understanding, mitigating hallucinatory outputs. We further introduce Plausibility Verification Process (PVP), a simple yet robust keyword constraint that effectively filters out sub-optimal keywords to enable the consistent triggering of counterfactual thinking in the model responses. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination and helps to broaden contextual understanding based on true visual clues.- Anthology ID:
- 2024.findings-emnlp.626
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10672–10689
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.626
- DOI:
- 10.18653/v1/2024.findings-emnlp.626
- Cite (ACL):
- Junho Kim, Kim Yeonju, and Yong Man Ro. 2024. What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10672–10689, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- What if…?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models (Kim et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.626.pdf