SenseAI: A Human-in-the-Loop Dataset for RLHF-Aligned Financial Sentiment Reasoning

ArXi:2604.05135v1 Announce Type: new The dataset consists of 1,439 labelled data points across 40 US-listed equities and 13 financial data categories, enabling direct integration into modern LLM fine-tuning pipelines. Through analysis, we identify several systematic patterns in model behavior, including a novel failure mode we term Latent Reasoning Drift, where models These findings suggest that LLM errors in financial reasoning are not random but occur within a predictable and correctable regime, ing the use of structured HITL data for targeted model improvement.