From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle, Anil Ramakrishna, Anubrata Das et al.|August 11, 2026arXiv

Key Takeaway

The field shifted from asking 'why did the model do that?' to 'how do we control what it does?'—and truthfulness is now the primary concern for LLM research, growing from absent to 37% of papers in just four years.

Summary

This paper analyzes six years of the TrustNLP workshop (2021-2026), tracking how AI safety research evolved from explaining static models to controlling generative systems.

safety evaluation alignment

Key Terms

mechanistic-interpretability post-hoc-explanation truthfulness safety-alignment