From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback
cs.AI, cs.LG, cs.SC
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- On Randomness in Agentic Evals
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- Categorizing Variants of Goodhart's Law
- LLM Evaluators Recognize and Favor Their Own Generations
- A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion
- Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
- FeClustRE: Hierarchical Clustering and Semantic Tagging of App Features from User Reviews
- TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems