Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation
本文针对对话生成中人格属性过度使用的问题,通过分析原因并提出SCONPOS方法抑制过度使用,同时引入PAS指标评估人格使用的适当性。
本文针对对话生成中人格属性过度使用的问题,通过分析原因并提出SCONPOS方法抑制过度使用,同时引入PAS指标评估人格使用的适当性。
本文提出HyperStyler,通过上下文感知风格导航和超网络解决低资源作者风格迁移问题,提高风格保真度和语义保留。
This work addresses the challenge that large language models often produce highly confident yet incorrect predictions, making reliable uncertainty estimation difficult. The authors propose Sem-ASMI, a training-agnostic uncertainty quantification method that, for the first time, links the fragility of attention subnetworks to prediction reliability. By perturbing attention heads and integrating BALD-based mutual information estimation with a semantic consistency kernel, Sem-ASMI identifies “high-confidence but fragile” errors within a single greedy decoding pass—eliminating the need for costly repeated sampling and automatically adapting to in-domain contexts. Evaluated across 12 grounded question-answering tasks, Sem-ASMI matches or outperforms the strongest baseline on 10 tasks and achieves significant gains on 3. Notably, it naturally degenerates to Maximum Softmax Probability (MSP) in parametric QA settings, confirming its domain adaptability.
This work proposes a high-quality multi-view panoptic segmentation method that operates without explicit 3D reconstruction or task-specific training. By encoding panoptic labels from input views into binary channels and leveraging a pre-trained large-scale view synthesis model for cross-view label propagation, the approach achieves zero-shot label transfer with a frozen model. It represents the first extension of large view synthesis models from appearance rendering to 3D scene understanding, employing cross-view attention mechanisms to ensure label consistency across perspectives. On ScanNet, the method attains segmentation quality comparable to state-of-the-art Gaussian-based 3D reconstruction approaches, while surpassing them by over 7 dB in novel view synthesis metrics. Furthermore, it demonstrates superior zero-shot transfer performance on Replica, outperforming existing methods without any fine-tuning.
This work addresses the inherent tension in large language models between compositional reasoning and knowledge retrieval, which are difficult to reconcile simultaneously. The authors propose Concrete Propositional Prompting (CPP), a novel framework that, for the first time, explicitly incorporates concrete propositional representations into prompt design. By structuring relevant factual propositions in a logically coherent manner, CPP seamlessly integrates logical composition with grounded knowledge without requiring model fine-tuning. The method demonstrates strong performance across diverse base models and parameter scales, achieving significant gains on medical reasoning benchmarks while remaining competitive on mathematical tasks. These results indicate that CPP effectively bridges the gap between compositional and knowledge-intensive reasoning, exhibiting both broad applicability and practical utility.
本文针对对话生成中人格属性过度使用的问题,通过分析原因并提出SCONPOS方法抑制过度使用,同时引入PAS指标评估人格使用的适当性。
本文提出HyperStyler,通过上下文感知风格导航和超网络解决低资源作者风格迁移问题,提高风格保真度和语义保留。
This work addresses the challenge that large language models often produce highly confident yet incorrect predictions, making reliable uncertainty estimation difficult. The authors propose Sem-ASMI, a training-agnostic uncertainty quantification method that, for the first time, links the fragility of attention subnetworks to prediction reliability. By perturbing attention heads and integrating BALD-based mutual information estimation with a semantic consistency kernel, Sem-ASMI identifies “high-confidence but fragile” errors within a single greedy decoding pass—eliminating the need for costly repeated sampling and automatically adapting to in-domain contexts. Evaluated across 12 grounded question-answering tasks, Sem-ASMI matches or outperforms the strongest baseline on 10 tasks and achieves significant gains on 3. Notably, it naturally degenerates to Maximum Softmax Probability (MSP) in parametric QA settings, confirming its domain adaptability.
This work proposes a high-quality multi-view panoptic segmentation method that operates without explicit 3D reconstruction or task-specific training. By encoding panoptic labels from input views into binary channels and leveraging a pre-trained large-scale view synthesis model for cross-view label propagation, the approach achieves zero-shot label transfer with a frozen model. It represents the first extension of large view synthesis models from appearance rendering to 3D scene understanding, employing cross-view attention mechanisms to ensure label consistency across perspectives. On ScanNet, the method attains segmentation quality comparable to state-of-the-art Gaussian-based 3D reconstruction approaches, while surpassing them by over 7 dB in novel view synthesis metrics. Furthermore, it demonstrates superior zero-shot transfer performance on Replica, outperforming existing methods without any fine-tuning.
This work addresses the inherent tension in large language models between compositional reasoning and knowledge retrieval, which are difficult to reconcile simultaneously. The authors propose Concrete Propositional Prompting (CPP), a novel framework that, for the first time, explicitly incorporates concrete propositional representations into prompt design. By structuring relevant factual propositions in a logically coherent manner, CPP seamlessly integrates logical composition with grounded knowledge without requiring model fine-tuning. The method demonstrates strong performance across diverse base models and parameter scales, achieving significant gains on medical reasoning benchmarks while remaining competitive on mathematical tasks. These results indicate that CPP effectively bridges the gap between compositional and knowledge-intensive reasoning, exhibiting both broad applicability and practical utility.