QLoRA微调在3B参数小型语言模型中对理论心智推理的研究：基于ToMBench的跨基准泛化研究

We investigate whether quantized low-rank adaptation (QLoRA) fine-tuning improves theory-of-mind (ToM) reasoning in a small language model, and whether apparent cross-benchmark transfer survives control for response-position bias. We fine-tuned 4-bit Qwen2.5-3B-Instruct with low-rank (LoRA) adapters on ToMBench under a story-disjoint split with five seeds. Because fine-tuning shifted the model’s answer-letter preference on every benchmark, we evaluated all models under cyclic permutation of answer options, placing each gold answer in every position once. Held-out ToMBench accuracy rose by +8.1