BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences

Researchers propose BridgeAlign, a preference-alignment pipeline for humanities and social sciences (HSS) tasks, which uses 210k synthetic preference samples to align Qwen3-8B, achieving the best average across 17 benchmarks against 11 strong baselines, leading on both human-preference and knowledge-based capabilities without trade-offs.

arXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models LLMs is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanities and social sciences HSS , where nuanced quality judgments matter more than objective correctness. This makes preference alignment a natural paradigm for broad HSS tasks. Yet existing methods are either costly or not tailored to broad HSS disciplines. We thus propose BridgeAlign, among the first preference-alignment pipelines for broad HSS disciplines, with three phases: i Seed Curation: curating HSS seed documents from web corpora via heuristic/LLM-based filtering and text refinement; ii Preference Data Synthesis: generating preference triplets via persona-based instruction inversion with Q&A consistency checks; iii Preference Optimization: moving beyond naive human-vs-model heuristics by first grounding preferences in HSS quality rubric, then generating transitional responses via controlled quality degradation to form near-boundary preference pairs for finer-grained quality discrimination. Aligning over 210k synthetic preference samples, BridgeAlign enables Qwen3-8B to achieve the best average across 17 benchmarks against 11 strong baselines; importantly, leading on both human-preference and knowledge-based capabilities at once, with no trade-off between them, as supported by extensive experiments and contextualized by existing theories.