Methods

Historical accounts tend to privilege a dominant and prestigious written language, even though multilingualism was and continues to be an ordinary condition of human life. In early modern East Asia, Neo-Confucian scholarship circulated principally in Literary Sinitic, but its dissemination and reception involved multiple linguistic communities, literary forms, and sociopolitical settings.

The multilingual capabilities of LLMs extend well beyond the reach of any individual historian, allowing us to recover, connect, and compare historical sources in Manchu, vernacular Chinese, and various forms of Literary Sinitic, including those practised in Korea. This work provides a basis for wider perspectives involving Japan, Okinawa, Vietnam, and Jesuit scholarship.

In early modern East Asia, literature, moral philosophy, and philology were overlapping scholarly pursuits, with individual scholars placing different emphases on each. Modern academic divisions, however, treat them as distinct fields of inquiry.

Our computational research environments, Pivot 機 and Traces 跡, employ specialized AI agents to bring literary, philosophical, and philological developments into an integrated field of view.

Pivot 機Beta Traces 跡Alpha

Intellectual history requires moving from individual passages and debates to larger formations such as schools of thought and literary and aesthetic movements. We also need to factor in that some scholars pursued forms of semiotics that questioned the a priori existence of fixed concepts. A further consideration is the contribution of thousands of lesser-known scholars who participated in the formation, development, and dissemination of these intellectual and cultural traditions.

We organize specialized AI agents in a research pipeline our team has developed, which we call agentic knowledge distillation. The agents analyse passages, synthesize higher-order interpretations of essays, and simulate debates among scholars. Each successive layer remains linked to the underlying records, allowing historians to examine the evidence at every interpretive level.

Agentic knowledge distillation is integrated into our Pivot 機 research environment.

Pivot 機Beta

LLMs can now produce interpretation-like readings of primary sources and secondary scholarship, extending the possibilities of computational hermeneutics beyond earlier approaches centred on word frequencies and semantic drift. The trade-off is that we know little about how models generate these sophisticated outputs. Evaluating model performance presents a further difficulty, since interpretive tasks involve a range of plausible responses rather than a single right or wrong answer.

We are currently experimenting with persona-vector steering, sparse autoencoders, and contrastive embedding models for literary-style analysis. We are also exploring evaluation methods involving expert focus groups and comparisons of outputs generated by multiple models, with particular attention paid to whether the machine interpretations are plausible, supported by historical evidence, and defensible against alternative readings.