这篇论文挺有意思，发现模型家族里真实头会继承，搞了个TruthProbe来减少幻觉，效果不错，适合研究模型可解释性和幻觉问题的人看。
论文发现，在Vicuna、Qwen2.5、LLaMA2和Mistral等模型家族中，上下文的真实性评分（Truth Scores）在指令微调或多模态适配后高度保留，与其注意头权重继承一致。作者提出TruthProbe软门控策略，通过放大上下文真实头而保留其他头贡献，在HaluEval上提升上下文真实性，并在POPE和CHAIR上减少多模态幻觉。基础LLM的真实头评分有效传递给微调后的LLM和多模态LLM后代。代码已开源。
The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages
Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages. It remains unclear whether a fundamental behavioral link exists between the foundational LLMs and downstream variants. We investigate this question by quantifying head-level context-truthfulness scores. Across diverse LLM and MLLM lineages, including Vicuna-, Qwen2.5-, LLaMA2-, and Mistral-based models, we find that Truth Scores are strongly preserved within model families, even after instruction tuning or multimodal adaptation. We further show that this inheritance is consistent with attention-head weight preservation, and that context-truthful heads attend to query-relevant evidence. Building on this finding, we propose TruthProbe, a soft-gating strategy that amplifies context-truthful heads while preserving other head contributions. TruthProbe improves contextual truthfulness on HaluEval and reduces multimodal hallucination on POPE and CHAIR, with base-LLM Truth Scores transferring effectively to their fine-tuned LLM and MLLM descendants. Code is available at https://github.com/miso-choi/TruthProbe.