3 papers
cs.LG2026
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
Leon Bergen, Usha Bhalla, Sidharth Baskaran +14
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. Th…
cs.LG2026
Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
Aaditya Vikram Prasad, Connor Watts, Jack Merullo +4
Language models trained on large-scale datasets have been shown to learn features that encode abstract concepts such as factuality or intent. Such features are traditionally used f…
cs.CL2020
Analyzing Gender Bias within Narrative Tropes
Dhruvil Gala, Mohammad Omar Khursheed, Hannah Lerner +2
Popular media reflects and reinforces societal biases through the use of tropes, which are narrative elements, such as archetypal characters and plot arcs, that occur frequently ac…