Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 3028-3046
Abstract
Hongxiang Zhang, Hao Chen, Muhao Chen, Tianyi Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications2024
- Detecting hallucinations in large language models using semantic entropyNature, 2024
- SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models2024
- Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding2024
- Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives2024
- FactGen: Faithful Text Generation by Factuality-aware Pre-training and Contrastive Ranking Fine-tuningJournal of Artificial Intelligence Research, 2023
- RARR: Researching and Revising What Language Models Say, Using Language Models2023
- A Contrastive Framework for Neural Text Generation2022
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022
- Did Aristotle Use a Laptop?A Question Answering Benchmark with Implicit Reasoning StrategiesTransactions of the Association for Computational Linguistics, 2021