ACL Findings2026
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives
Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang
摘要
Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang. Findings of the Association for Computational Linguistics: ACL 2026. 2026.
问 Lune
尽管问，回答会引用原文。
Lune 会读完全文和相关的 Paper，每个回答都附上所依据的原文段落。
它引用的 Paper5
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning 等NeurIPS 2023 · 10,924 次引用
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford, Jong Wook Kim, Tao Xu, Greg Brockman 等ICML 2023 · 6,966 次引用
- SALMONN: Towards Generic Hearing Abilities for Large Language ModelsChangli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen 等ICLR 2024 · 557 次引用
- Listen, Think, and UnderstandYuan Gong, Hongyin Luo, Alexander H. Liu, Leonid Karlinsky 等ICLR 2024 · 247 次引用
- SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational AbilitiesDong Zhang, Shimin Li, Xin Zhang, Jun Zhan 等EMNLP Findings 2023 · 189 次引用
相关 Paper
- Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention LoopingYao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang 等ACL Findings 2026
- D²-RAG: Dual-Decision Retrieval-Augmented Generation via Multi-Dimensional Uncertainty and Utility-Aware DecodingJinshuo Zhang, Xiaoding Zhou, Weiyu Zhang, Guoqiang Chen 等ACL Findings 2026
- MorphoBench: A Benchmark with Difficulty Adaptive to Model ReasoningXukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong 等ACL Findings 2026
- Comprehensive Benchmarking of Long-Form Speech Generation in Diverse ScenariosChanghao Pan, Rui Yang, Han Wang, Zhuan Zhou 等ACL Findings 2026
- Do Vision-Language Models Have Internal World Models? Towards an Atomic EvaluationQiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen 等ACL Findings 2025 · 3 次引用
