{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/atomic-consistency-preference-optimization","title":"Atomic Consistency Preference Optimization for Long-Form Question Answering","arxiv_id":"2505.09039","date":"2025-05-14","proceeding":null,"authors":["Jingfeng Chen","Raghuveer Thirukovalluru","Junlin Wang","Kaiwei Luo","Bhuwan Dhingra"],"abstract":"Large Language Models (LLMs) frequently produce factoid hallucinations - plausible yet incorrect answers. A common mitigation strategy is model alignment, which improves factual accuracy by training on curated factual and non-factual pairs. However, this approach often relies on a stronger model (e.g., GPT-4) or an external knowledge base to assess factual correctness, which may not always be accessible. To address this, we propose Atomic Consistency Preference Optimization (ACPO), a self-supervised preference-tuning method that enhances factual accuracy without external supervision. ACPO leverages atomic consistency signals, i.e., the agreement of individual facts across multiple stochastic responses, to identify high- and low-quality data pairs for model alignment. By eliminating the need for costly GPT calls, ACPO provides a scalable and efficient approach to improving factoid question-answering. Despite being self-supervised, empirical results demonstrate that ACPO outperforms FactAlign, a strong supervised alignment baseline, by 1.95 points on the LongFact and BioGen datasets, highlighting its effectiveness in enhancing factual reliability without relying on external models or knowledge bases.","url_abs":"https://arxiv.org/abs/2505.09039v1","url_pdf":"https://arxiv.org/pdf/2505.09039v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"atomic-consistency-preference-optimization","repo_url":"https://github.com/jingfengsteven/acpo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"long-form-question-answering","task_name":"Long Form Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}