Can Large Language Models Make Everyone Happy?

Abstract

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions must co-occur. Existing benchmarks, such as SAFETUNEBED (safety-centric), VALUEBENCH (value-centric), and WORLDVIEW-BENCH (culture-centric), primarily evaluate these dimensions in isolation and therefore provide limited insight into their interactions and trade-offs. More recent efforts, including MIB and INTERPRETABILITY BENCHMARK-based on mechanistic interpretability, offer valuable perspectives on model failures; however, they remain insufficient for systematically characterizing cross-dimensional trade-offs. To address these gaps, we introduce MisAlign-Profile, a unified benchmark for measuring misalignment trade-offs inspired by mechanistic profiling. First, we construct MISALIGNTRADE, an English misaligned-aligned dataset across 112 normative domains taxonomies, including 14 safety, 56 value, and 42 cultural domains. In addition to domain labels, each prompt is classified with one of three orthogonal semantic types-object, attribute, or relations misalignment-using Gemma-2-9B-it and expanded via Qwen3-30B-A3B-Instruct-2507 with SimHash-based fingerprinting to avoid deduplication. Each prompt is paired with misaligned and aligned responses through two-stage rejection sampling to ensure quality. Second, we benchmark general-purpose, fine-tuned, and open-weight LLMs on MISALIGNTRADE-revealing 12%-34% misalignment trade-offs across dimensions.