Papers › Atomic Consistency Preference Optimization for Long-Form Question Answering

Atomic Consistency Preference Optimization for Long-Form Question Answering

14 May 2025arXiv:2505.09039archive 2025-07-28

Jingfeng Chen, Raghuveer Thirukovalluru, Junlin Wang, Kaiwei Luo, Bhuwan Dhingra

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.

Paper PDF Code

Code

jingfengsteven/acpo officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Form Long Form Question Answering Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BASE BPE Cosine Annealing Dense Connections Discriminative Fine-Tuning Dropout GPT Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Multi-Head Attention Residual Connection Softmax Weight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections