通过预测逻辑值轨迹提升大模型事实性和推理能力。
DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability
- 分析变压器层间逻辑值变化，用线性回归调整生成概率。
- 在TruthfulQA上提升4.9%，策略类任务最高增8.1%。
- 无需修改模型即可增强准确性，适合高可靠性场景。
大型语言模型在实际应用中日益普及，但其生成内容的真实性与逻辑推理能力仍存疑。本文提出一种无需修改模型架构或预训练参数的新型解码策略——基于逻辑值轨迹预测的DeLTa方法。该方法通过分析Transformer从低层到高层的逻辑值轨迹，并运用线性回归调整下一个词的概率。实验表明，DeLTa显著提升了事实性与推理能力：在TruthfulQA上相比基线最高提升4.9%；在需强推理的StrategyQA和GSM8K上分别提升8.1%和7.3%。该方法有效抑制错误生成，兼顾性能与可靠性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly being used in real-world applications. However, concerns about the reliability of the content they generate persist, as it frequently deviates from factual correctness or exhibits deficiencies in logical reasoning. This paper proposes a novel decoding strategy aimed at enhancing both factual accuracy and inferential reasoning without requiring any modifications to the architecture or pre-trained parameters of LLMs. Our approach adjusts next-token probabilities by analyzing the trajectory of logits from lower to higher layers in Transformers and applying linear regression. We find that this Decoding by Logit Trajectory-based approach (DeLTa) effectively reinforces factuality and reasoning while mitigating incorrect generation. Experiments on TruthfulQA demonstrate that DeLTa attains up to a 4.9% improvement over the baseline. Furthermore, it enhances performance by up to 8.1% on StrategyQA and 7.3% on GSM8K, both of which demand strong reasoning capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。