Research Papers 论文研究 5h ago Updated 1h ago 更新于 1小时前 46

Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection 掩码背后:解构DAPF痴呆检测中的表征与忠实性

DAPF (Domain-Adapted models via Prompt-based Fine-tuning) achieves the best dementia detection performance among tested models, with accuracy=0.83 and macro-F1=0.83 Diagnosis information is most recoverable from the [MASK] token representation in DAPF, confirming its representational strength Token-level explanation faithfulness does not match representational performance; attributions primarily reflect language task vocabulary, discourse markers, and transcription artifacts rather than clinical DAPF框架将痴呆检测转化为掩码标记预测任务,在低资源场景下实现0.83准确率和0.83 macro-F1的最佳性能 诊断信息可从[MASK]表示中有效恢复,但表征优势未延伸至标记级别的解释忠实度 DAPF的归因主要反映语言任务词汇、话语标记和转录伪影,而非真正的诊断特征 扰动测试显示弱或负面效果,表明掩码标记接口虽能确定诊断信息,但无法产生忠实于标记级别的解释

58
Hot 热度
74
Quality 质量
67
Impact 影响力

Analysis 深度分析

TL;DR

  • DAPF (Domain-Adapted models via Prompt-based Fine-tuning) achieves the best dementia detection performance among tested models, with accuracy=0.83 and macro-F1=0.83
  • Diagnosis information is most recoverable from the [MASK] token representation in DAPF, confirming its representational strength
  • Token-level explanation faithfulness does not match representational performance; attributions primarily reflect language task vocabulary, discourse markers, and transcription artifacts rather than clinically meaningful signals
  • Perturbation tests reveal weak or even negative effects, indicating that the masked-token interface determines diagnosis without producing faithful token-level explanations
  • The study highlights a critical gap between predictive performance and interpretability in prompt-based domain-adaptive models for low-resource medical screening

Why It Matters

This work is directly relevant to AI practitioners building explainable systems for healthcare applications, as it demonstrates that strong predictive performance does not guarantee faithful explanations—a key concern for clinical deployment. For researchers, it provides empirical evidence that [MASK]-based prompt interfaces may encode diagnostic information in ways that are not accessible through standard attribution methods, urging caution when relying on token-level explanations for high-stakes decisions.

Technical Details

  • The DAPF framework reformulates dementia detection as a diagnosis-related masked-token prediction task, leveraging prompt-based fine-tuning on domain-adapted language models for spoken-language analysis
  • Interpretability was evaluated using a variety of probing and analysis techniques, including perturbation-based faithfulness tests, to assess whether model attributions align with actual diagnostic signals
  • DAPF outperformed strong baselines on accuracy (0.83) and macro-F1 (0.83), with the [MASK] representation showing the highest recoverability of diagnosis information among all analyzed representations
  • Attribution analysis revealed that DAPF's token-level explanations were dominated by non-clinical factors: language task vocabulary, discourse markers, and ASR transcription artifacts, with perturbation tests yielding weak or negative faithfulness effects

Industry Insight

  • Practitioners should not assume that high-performing prompt-based models produce trustworthy explanations; representational capacity and explanation faithfulness are decoupled, requiring explicit interpretability validation before clinical deployment
  • For low-resource medical screening applications, investing in faithfulness-aware evaluation (e.g., perturbation tests) alongside standard accuracy metrics is essential to avoid deploying models whose explanations mislead clinicians
  • The findings suggest that alternative interpretability approaches beyond token-level attribution—such as representation-level probing or latent-space analysis—may be needed to unlock the diagnostic reasoning embedded in masked-token interfaces

TL;DR

  • DAPF框架将痴呆检测转化为掩码标记预测任务,在低资源场景下实现0.83准确率和0.83 macro-F1的最佳性能
  • 诊断信息可从[MASK]表示中有效恢复,但表征优势未延伸至标记级别的解释忠实度
  • DAPF的归因主要反映语言任务词汇、话语标记和转录伪影,而非真正的诊断特征
  • 扰动测试显示弱或负面效果,表明掩码标记接口虽能确定诊断信息,但无法产生忠实于标记级别的解释

为什么值得看

本文揭示了可解释AI在医疗诊断应用中的关键矛盾——模型性能与可解释性之间的脱节。对于AI从业者和医疗AI研究者而言,这提醒我们在追求高准确率的同时,必须审慎评估模型决策过程的真实可解释性,避免被表面性能误导。

技术解析

  • DAPF(Domain-Adapted models via Prompt-based Fine-tuning)框架将痴呆检测重新定义为诊断相关的掩码标记预测任务,通过提示微调实现领域自适应
  • 研究采用多种探测和分析技术评估DAPF及其强基线模型的可解释性,发现[MASK]表示中蕴含的诊断信息可被有效恢复
  • 标记级别的归因分析显示DAPF主要关注语言任务词汇、话语标记和转录伪影,而非临床诊断特征
  • 扰动测试(perturbation tests)结果进一步验证了归因的不可靠性,显示弱或负面效果

行业启示

  • 医疗AI模型的性能评估需超越准确率指标,建立多维度的可解释性验证框架,特别是在低资源场景下
  • 提示微调等新兴范式虽能提升性能,但其内部决策机制可能隐藏"黑箱"风险,需开发更精细的归因分析方法
  • 研究者和从业者应重新审视"可解释性"的定义——表征层面的可恢复性不等于标记层面的忠实解释,两者需分开评估

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Healthcare AI 医疗AI Research 科学研究 LLM 大模型 Fine-tuning 微调 Evaluation 评测