Ptolemy: A Semantic Map of Exploratory Data Analysis
该研究通过构建一个名为Ptolemy的语义地图来解决探索性数据分析过程中难以追踪已分析内容的问题，利用结构化描述生成嵌入式位置表示每个分析步骤，以提高全局定位和局部比较能力。
0 citationsRead paper
Selected work
Representative Papers
AppetiteCheck: Feasibility of Momentary Vagus Nerve Stimulation as an Implicit Intervention for Eating Behavior
研究通过使用非侵入性迷走神经刺激方法，在24名参与者中测试了其对减少过量和情绪化进食行为的有效性，结果显示该方法能显著降低食量并减慢进食速度。
0 citationsRead paper
Social.Wiki: A Web Held in Common
本文提出Social.Wiki系统，利用AI工具使非编程用户也能协作编辑社交网站，旨在解决网站所有者与用户利益不一致的问题。
0 citationsRead paper
Measuring Cross-Task Behavioral Consistency in Language Model Agents
论文提出行为一致性度量(BCM)方法，用于量化语言模型代理在不同任务间的行为一致性，补充了仅基于结果指标的评估方式。
0 citationsRead paper
Training Language Models to Explain Their Own Computations
This work investigates whether language models (LMs) can leverage “privileged access” to their internal computations to generate accurate, generalizable natural language explanations. Method: We introduce *self-explanation*—a novel paradigm wherein high-quality explanatory annotations are automatically generated via interpretability techniques (e.g., feature attribution, causal mediation analysis), and a pretrained LM is fine-tuned on only tens of thousands of such examples to produce explanations of feature encoding, activation-level causal structure, and input influence. Contribution/Results: Experiments demonstrate that self-explaining LMs significantly outperform strong external explainer models and generalize robustly to unseen queries with minimal training. Crucially, this is the first systematic empirical validation that privileged access to internal states yields substantial explanatory value—enabling scalable, low-cost model interpretation without requiring architectural modification or expensive human annotation.
0 citationsRead paper
Recent publications
Latest Papers
Ptolemy: A Semantic Map of Exploratory Data Analysis
该研究通过构建一个名为Ptolemy的语义地图来解决探索性数据分析过程中难以追踪已分析内容的问题，利用结构化描述生成嵌入式位置表示每个分析步骤，以提高全局定位和局部比较能力。
0 citationsRead paper
AppetiteCheck: Feasibility of Momentary Vagus Nerve Stimulation as an Implicit Intervention for Eating Behavior
研究通过使用非侵入性迷走神经刺激方法，在24名参与者中测试了其对减少过量和情绪化进食行为的有效性，结果显示该方法能显著降低食量并减慢进食速度。
0 citationsRead paper
Social.Wiki: A Web Held in Common
本文提出Social.Wiki系统，利用AI工具使非编程用户也能协作编辑社交网站，旨在解决网站所有者与用户利益不一致的问题。
0 citationsRead paper
Measuring Cross-Task Behavioral Consistency in Language Model Agents
论文提出行为一致性度量(BCM)方法，用于量化语言模型代理在不同任务间的行为一致性，补充了仅基于结果指标的评估方式。
0 citationsRead paper
Training Language Models to Explain Their Own Computations
This work investigates whether language models (LMs) can leverage “privileged access” to their internal computations to generate accurate, generalizable natural language explanations. Method: We introduce *self-explanation*—a novel paradigm wherein high-quality explanatory annotations are automatically generated via interpretability techniques (e.g., feature attribution, causal mediation analysis), and a pretrained LM is fine-tuned on only tens of thousands of such examples to produce explanations of feature encoding, activation-level causal structure, and input influence. Contribution/Results: Experiments demonstrate that self-explaining LMs significantly outperform strong external explainer models and generalize robustly to unseen queries with minimal training. Crucially, this is the first systematic empirical validation that privileged access to internal states yields substantial explanatory value—enabling scalable, low-cost model interpretation without requiring architectural modification or expensive human annotation.
0 citationsRead paper