decision-rules

This paper presents ERGO, an error-driven method for iterative prompt optimization in text classification that diagnoses classification failures and generates targeted decision rules, achieving best accuracy on tasks where errors concentrate in specific confused label pairs.

This paper critiques the use of pairwise comparisons for learning human preferences, arguing that internal pluralism (multiple conflicting priorities) undermines the standard approach. It proposes a formal model and suggests that allowing indecision can improve learning efficiency.

Trace2Policy extracts human-readable decision rules from expert behavior traces and iteratively refines them via error-driven skill refinement, outperforming pure LLM baselines on compliance-sensitive tasks in logistics.