method · first seen 8 Oct 2026
preference alignment
Tuning a model with pairs of preferred and dispreferred outputs to reduce undesired behaviors.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible EvidencePapers · 8 Oct 2026 · Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang
- Differential Privacy Protected Preference Alignment on Survey Derived DataPapers · 12 Oct 2026 · Xiuyuan Qi, Yi Wang, Wenjie Wang
- Aligning Cultural Behaviors in Arabic Language Models via PreferencesPapers · 18 Oct 2026 · Junhong Liang, Daniil Orel, Saeed Almheiri, Bilal Elbouardi, Younes Samih, Abed…
- When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-TrainingPapers · 23 Oct 2026 · Qi Xu, Zijie Lei, Zhifei Deng, Zhigang Hua, Luke Simon
- A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training AlignmentPapers · 24 Oct 2026 · Xiangjing An, Zhibin Jiao, Aiting Chen
Latest sources
- A Comprehensive Framework for All Stages of Large-Model Training: From Data and Tokenization, through Pretraining, to Post-Training AlignmentPapers · 24 Oct 2026 · Xiangjing An, Zhibin Jiao, Aiting Chen
- When Does Pre-Trained Capacity Help Causal Learning? From Scalar Prediction to Counterfactual Post-TrainingPapers · 23 Oct 2026 · Qi Xu, Zijie Lei, Zhifei Deng, Zhigang Hua, Luke Simon
- Aligning Cultural Behaviors in Arabic Language Models via PreferencesPapers · 18 Oct 2026 · Junhong Liang, Daniil Orel, Saeed Almheiri, Bilal Elbouardi, Younes Samih, Abed…
- Differential Privacy Protected Preference Alignment on Survey Derived DataPapers · 12 Oct 2026 · Xiuyuan Qi, Yi Wang, Wenjie Wang
- Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible EvidencePapers · 8 Oct 2026 · Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang