提出MR-IQA-2，用细粒度信用分配让多模态大模型在图像质量评估中的推理更忠实。
arXiv:2608.18579v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (I…
揭秘LLM推荐系统幻觉：模型是否自知？联合审计幻觉率与置信度校准，为目录忠实度提供新视角。
arXiv:2608.10008v1 Announce Type: cross Abstract: LLM recommenders for top-$K$ item suggestion regularly emit titles outside the target catalog. Prior…
用反事实模拟训练提升思维链忠实度，解读大模型推理黑箱的新思路。
arXiv:2602.20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM p…
arXiv新研究聚焦文档转播客（Doc2Podcast）的忠实度问题，提出提升内容一致性的方法，减少AI生成幻觉。
arXiv:2607.21961v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate long-form conversational content such a…
用强化学习直接优化大模型自解释的忠实性，让AI的推理更可信。
arXiv:2607.21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explan…
大模型红队评估新框架，聚焦忠实度检验，为高风险场景部署提供可靠性参考，安全团队值得关注。
arXiv:2606.25476v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language proces…
深入剖析LLM代词保真失效的机制，揭示推理、重复与偏见间的复杂关系。
arXiv:2606.16407v1 Announce Type: cross Abstract: Faithful and robust pronoun use is important for fair and coherent generations, yet large language m…
提出控制保留信息的新方法，可靠评估Decoder-only LLM的归因忠实度，为可解释性研究提供关键视角。
arXiv:2601.03089v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet …
谷歌AI概览（AIO）覆盖20亿用户，首篇系统测评其生成答案的质量、忠实度及对出版商的影响。
arXiv:2605.14021v1 Announce Type: cross Abstract: Google AI Overviews (AIOs) are arguably the most widely encountered deployment of generative AI, rea…
106本小说16种语言，130k段落揭示大模型文学翻译流畅性与忠实度间的微妙平衡
arXiv:2605.15282v1 Announce Type: new Abstract: Literary translation requires balancing target-language fluency with faithfulness to the source. Recen…