{"work":{"id":"39a08cdc-3986-4994-baf0-91e8ddf1b855","openalex_id":null,"doi":null,"arxiv_id":"2302.12192","raw_key":null,"title":"Aligning Text-to-Image Models using Human Feedback","authors":null,"authors_text":"Kimin Lee, Hao Liu, Moonkyung Ryu, Olivia Watkins, Yuqing Du, Craig Boutilier","year":2023,"venue":"cs.LG","abstract":"Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such models using human feedback, comprising three stages. First, we collect human feedback assessing model output alignment from a set of diverse text prompts. We then use the human-labeled image-text dataset to train a reward function that predicts human feedback. Lastly, the text-to-image model is fine-tuned by maximizing reward-weighted likelihood to improve image-text alignment. Our method generates objects with specified colors, counts and backgrounds more accurately than the pre-trained model. We also analyze several design choices and find that careful investigations on such design choices are important in balancing the alignment-fidelity tradeoffs. Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.","external_url":"https://arxiv.org/abs/2302.12192","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-22T23:42:16.514390+00:00","pith_arxiv_id":"2302.12192","created_at":"2026-05-09T06:15:37.382447+00:00","updated_at":"2026-05-22T23:42:16.514390+00:00","title_quality_ok":true,"display_title":"Aligning Text-to-Image Models using Human Feedback","render_title":"Aligning Text-to-Image Models using Human Feedback"},"hub":{"state":{"work_id":"39a08cdc-3986-4994-baf0-91e8ddf1b855","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":37,"external_cited_by_count":null,"distinct_field_count":7,"first_pith_cited_at":"2023-04-13T18:22:40+00:00","last_pith_cited_at":"2026-05-19T12:18:15+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-05T15:19:12.384677+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":14},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":12},{"context_polarity":"unclear","n":2},{"context_polarity":"use_method","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}