Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Anonymous

Abstract: Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM's performance may be influenced by the presentation of answer choices, leaving the selection bias during Supervised Fine-Tuning (SFT) unexplored. In this paper, we reveal that selection bias persists in the SFT phase of LLMs, primarily due to the LLM's inadequate Multiple Choice Symbol Binding (MCSB) capability. This limitation implies that the model struggles to associate the answer options with their corresponding symbols effectively. To enhance the model's MCSB capability, we first incorporate option contents into the loss function and subsequently adjust the weights of the option symbols and contents, guiding the model to understand the option content of the current symbol. Based on this, we introduce an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback (PIF). PIF constructs negative instances by randomly combining the incorrect option contents with all candidate option symbols, and proposes a point-wise loss to provide feedback on these negative samples into LLMs. Our experimental results demonstrate that PIF significantly reduces the model's selection bias by improving its MCSB capability. Remarkably, PIF exhibits a substantial enhancement in the accuracy for MCQs.

Paper Type: long

Research Area: Semantics: Sentence-level Semantics, Textual Inference and Other areas

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English