{"slug": "bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences", "title": "BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences", "summary": "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.", "body_md": "arXiv:2607.27366v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences", "canonical_source": "https://www.machinebrief.com/news/bridgealign-bridging-preference-alignment-for-humanities-and-0jek", "published_at": "2026-07-31 04:00:00+00:00", "updated_at": "2026-07-31 04:36:14.861023+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["BridgeAlign", "Qwen3-8B", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences", "markdown": "https://wpnews.pro/news/bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences.md", "text": "https://wpnews.pro/news/bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences.txt", "jsonld": "https://wpnews.pro/news/bridgealign-bridging-preference-alignment-for-humanities-and-social-sciences.jsonld"}}