conftrace_

goal alignment

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) ai safety (2) instrumental convergence (1) goal reasoning (1) misspecified objective (1) reflective reasoning (1) power seeking (1) world-grounded reasoning (1) reasoning backbone (1) goal state divergence (1)

Papers

Inferring Implicit Goals Across Differing Task Models AAAI 2026 Reducing Goal State Divergence with Environment Design AAAI 2026 AI-LieDar : Examine the Trade-off Between Utility and Truthfulness in LLM Agents NAACL 2025 ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection EMNLP 2025 Goal Alignment: Re-analyzing Value Alignment Problems Using Human-Aware AI AAAI 2024 Asymptotically Unambitious Artificial General Intelligence AAAI 2020