conftrace_

interpretability tool

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature-level perturbation (1) feature-level adversarial perturbation (1) feature-level adversary (1) world modeling (1) user simulation (1) large language model (1) image generator (1) factual reasoning (1) dialog generation (1) dialogue system (1)

Papers

Factuality Evaluation Using Reasoning and World Modeling AAAI 2026 SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation EACL 2026 Robust Feature-Level Adversaries are Interpretability Tools NeurIPS 2022