Recent Work

Understanding Large Language Models Demands Distinguishing Human Projection from Machine Cognition

Lingyu Li · Yan Teng · Yingchun Wang · Xia Hu

Current efforts to understand LLMs are largely metaphorical. Researchers map LLMs onto familiar domains, from physics and neuroscience to psychology and sociology, each illuminating specific facets while obscuring others. We chart these metaphors across mechanistic, behavioral, and interactive scales and delineate their explanatory boundaries. Crucially, this metaphorical projection creates a recursive loop of anthropomorphism, fueling the genuine understanding versus pattern matching impasse. As an alternative approach, we propose machine experientialism, positing that LLMs build their own form of understanding from training corpora. The priority shifts from cataloging LLMs' human-like traits to uncovering their distinct logic that emerges from this text-based world.

Mechanistic Origin of Moral Indifference in Language Models

Lingyu Li · Yan Teng · Yingchun Wang

Just as money quantifies qualities, the tokenization process in LLMs maps discrete, semantically distinct concepts from genocide to apple into a unified embedding space and thus share the same ontological status as probability distributions to be calculated, rendering the Moral Indifference inevitable. Along our Machine Experientialsm philosophy, we verify and remedy this indifference in LLMs' latent representations, utilizing 251k moral vectors constructed upon Prototype Theory and the Social-Chemistry-101 dataset. We also propose a targeted representational alignment using Sparse Autoencoders, that naturally improves moral reasoning and granularity. Endogenous alignment requires a transformation from corrections to cultivation.

The Other Mind: How Language Models Exhibit Human Temporal Cognition

Lingyu Li · Yang Yao · Yixu Wang · Chunbo Li · Yan Teng · Yingchun Wang

Large Language Models spontaneously establish a subjective temporal reference point and adhere to the Weber-Fechner law: perceiving temporal distance with logarithmic compression mirroring human cognition. Through analysis at neuronal, representational, and informational levels, we uncover the mechanisms behind this emergence and propose an experientialist perspective. LLM cognition is a subjective construction of the external world by its internal representational system. This framing implies that the key risk is not that AI becomes too human-like, but that it develops powerful, alien cognitive frameworks we cannot intuitively predict, pointing toward a new direction for AI alignment that guides internal constructions rather than policing external behavior.