Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To tackle this challenge, we propose an interactive system that helps users obtain insights into the reliability of the generated text. Our approach is based on the idea that the self-consistency of multiple samples generated by the same LLM relates to its confidence in individual claims in the generated texts. Using this idea, we design RELIC, an interactive system that enables users to investigate and verify semantic-level variations in multiple long-form responses. This allows users to recognize potentially inaccurate information in the generated text and make necessary corrections. From a user study with ten participants, we demonstrate that our approach helps users better verify the reliability of the generated text. We further summarize the design implications and lessons learned from this research for inspiring future studies on reliable human-LLM interactions.

This forecast is part of the Dividends Package, as one of I Know First's quantitative investment solutions. We determine the best stocks carrying a dividend by screening our database daily using our advanced algorithm. Package Name: Dividend Stocks Forecast Recommended Positions: Long Forecast Length: 1 Year (2/7/21 – 2/7/22) I Know First Average: 41.1% For this 1 Year forecast the algorithm had successfully predicted 10 out of 10 movements. The highest trade return came from BHLB, at 61.06%. The suggested trades for CMA and STLD also had notable 1 Year yields of 55.88% and 55.01%, respectively.