Tencent Advertising Technology
Aug 13, 2024 · Artificial Intelligence
Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors
This paper investigates selection bias in large language models for multiple‑choice tasks, proposes metrics to quantify symbol‑content binding, introduces Reweighting Symbol‑Content Binding (RSCB) and Point‑wise Intelligent Feedback (PIF) methods, and demonstrates their effectiveness in reducing bias and improving accuracy, including a real‑world Tencent advertising feature‑evaluation deployment.
Multiple Choicepointwise feedbackreinforcement learning
0 likes · 16 min read