arXiv:2610.19035v1 Announce Type: new
Abstract: Pluralistic alignment needs to accommodate diverse preferences under limited human feedback. Using AI simulators to label preference comparisons reduce...
By Ruomeng Ding, Tianwei Gao, Lianrui Geng, Mohit Bansal, Zhun Deng
arXiv:2607. 25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed.
By Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Siheng Wang, Haoyan Xu, Yuqi Li, Chenhao Wei, Zhengdao Li, Rongchao Zhang, Guang Yang, Yidong Wang, Junhao Dong
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
By Hyung Gyu Rho
arXiv:2502.14643v3 Announce Type: replace
Abstract: Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF),...
By Gengxu Li, Tingyu Xia, Yi Chang, Yuan Wu
The paper introduces DIAL, a framework that uses large language models (LLMs) as judges while mitigating position bias and aligning their judgments with human preferences. DIAL separates judge‑specific position effects, learns shared structure in debiased LLM preferences, and adaptively calibrates this structure toward human targets using limited human comparisons. Experiments on simulations and three human‑preference benchmarks show that DIAL remains robust to unbalanced response order, achieves strong human‑aligned rankings with few labels, and adapts when LLM information is imperfect, supported by a real‑data study of over 410K judgments from 21 LLM judges.
By Zesheng Cai, Yingqi Fan, Sichang Chen, Jin-Hong Du
arXiv:2608.30902v1 Announce Type: new
Abstract: Adapting large language models to user-specific preferences is often constrained by the cost of human annotation, making preference optimisation imprac...
By Alessio Galatolo, Meriem Beloucif
arXiv:2606. 01561v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO).
By Xiwen Chen, Wenhui Zhu, Jingjing Wang, Peijie Qiu, Zhipeng Wang, Huayu Li, ZhengXiao He, Xuanzhao Dong, Prayag Tiwari, Mingkun Xu, Yujian Xiong, Feng Luo, Abolfazl Razi, Brendan Hogan Rappazzo, Anderson Schneider, Yuriy Nevmyvaka
SCOPE is a framework that calibrates an acceptance threshold for large language models used as pairwise judges, ensuring that the error rate among non-abstained judgments does not exceed a user-specified level α. It introduces Bidirectional Preference Entropy (BPE) to provide a bias-neutral uncertainty signal by querying the judge in both response positions and converting the averaged preference probability into an entropy-based score. Across multiple pairwise judging benchmarks, BPE outperforms standard confidence proxies in calibration and discrimination, while SCOPE consistently meets the target risk bound (empirical FDR ≈0.097–0.099 at α=0.10) and retains substantial coverage, accepting up to 2.4× more judgments under the same risk constraint.
By Sher Badshah, Ali Emami, Hassan Sajjad
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.
By Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf
arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.
By Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim, Yu Jin Kim, Youngsoo Jang, Moontae Lee, Jungwoo Lee
arXiv:2606. 19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models.
By Jiangze Han, Vineet Goyal, Will Ma
arXiv:2512.23067v3 Announce Type: replace
Abstract: Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption th...
By Fady Rezk, Yuangang Pan, Chuan-Sheng Foo, Xun Xu, Nancy Chen, Henry Gouk, Timothy Hospedales