← 研踪 PaperTrailarXiv:2610.37868 · v1
Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions
首次提交 2026-10-28 03:13
版本更新 2026-10-28 03:13
雷达观测 2026-10-30 10:23
摘要
Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches to matching the full distribution of human ratings mainly rely on output-level calibration or parameter fine-tuning. We propose Human-Residual Steering (HRS), to our knowledge the first method to align frozen LLM judges with human judgment distributions through learned hidden-state interventions. An oracle analysis shows that low-rank corrections at a single layer remove most of the discrepancy between judge and human distributions. HRS learns to predict such corrections from the judge's hidden representation and rating logits, training on individual annotations with proper scoring rules for ordinal and nominal judgments and optimising through the frozen downstream layers. Across 14 benchmarks and four judges from three model families, HRS outperforms all evaluated frozen-weight baselines. With Qwen2.5-7B, it achieves the lowest Jensen-Shannon distance on 13 of 14 benchmarks, reducing the mean from 0.565 to 0.352 versus 0.377 for the strongest calibrator. HRS also raises mean Spearman correlation with aggregate human scores from 0.449 to 0.579, improves population-level estimation under limited annotation budgets, and trains about 88 times fewer parameters than distributional fine-tuning at a modest cost in alignment.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-28 03:13 · 最新观测版本
Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions
Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches to matching the full distribution of human ratings mainly rely on output-level calibration or parameter fine-tuning. We propose Human-Residual Steering (HRS), to our knowledge the first method to align frozen LLM judges with human judgment distributions through learned hidden-state interventions. An oracle analysis shows that low-rank corrections at a single layer remove most of the discrepancy between judge and human distributions. HRS learns to predict such corrections from the judge's hidden representation and rating logits, training on individual annotations with proper scoring rules for ordinal and nominal judgments and optimising through the frozen downstream layers. Across 14 benchmarks and four judges from three model families, HRS outperforms all evaluated frozen-weight baselines. With Qwen2.5-7B, it achieves the lowest Jensen-Shannon distance on 13 of 14 benchmarks, reducing the mean from 0.565 to 0.352 versus 0.377 for the strongest calibrator. HRS also raises mean Spearman correlation with aggregate human scores from 0.449 to 0.579, improves population-level estimation under limited annotation budgets, and trains about 88 times fewer parameters than distributional fine-tuning at a modest cost in alignment.
查看此版本解读 →查看此版本原文 ↗