Rekod bukti kaedah

Direct Preference Optimization

Direct Preference Optimization (DPO) is a training method introduced by Rafailov et al. in 2023 that aligns language models with human preferences without requiring an explicit reward model. By directly optimizing for preference pairs (better response vs worse response), DPO simplifies the training pipeline compared to reinforcement learning from human feedback (RLHF).

Sources recorded, not reviewed

Rekod sumber

Petikan disalin secara verbatim daripada rekod sumber kaedah. Tiada pengesahan peringkat tuntutan disimpulkan daripadanya.

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Rekod kaedah taksonomik · ml-model / deep-learning

Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023). Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290. · URL

Buka kaedah penuh

Tuntutan yang dikurasi

Tuntutan disimpan dalam lejar bukti, setiap satu dengan penilaiannya sendiri.

Tiada tuntutan terkurasi lagi

Pandangan ini tidak mencipta penilaian tuntutan apabila lejar tiada.

Kaedah berkaitan

Dijana daripada graf kaedah dan ditunjukkan sebagai perhubungan yang dicadangkan mesin — tiada tuntutan bukti disimpulkan.

Same method familyLatent Diffusion Modelsmachine-suggested · Relational suggestion, not evidence.Same method familyMamba (State Space Model)machine-suggested · Relational suggestion, not evidence.Same method familyMasked Autoencodersmachine-suggested · Relational suggestion, not evidence.Same method familyQLoRAmachine-suggested · Relational suggestion, not evidence.