Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
The paper proposes a new dataset and method to leverage implicit user feedback to improve the accuracy of Large Language Models.
The paper introduces a new dataset and method to leverage implicit user feedback, which is a novel approach compared to existing methods that rely on explicit feedback.
Before reading this…
Applications
- →Improving the accuracy of Large Language Models
To understand this paper, make sure you know these concepts first:
- Understanding of Large Language Modelsfind papers →
- Knowledge of machine learning and data collectionfind papers →
Abstract
More Like ThisTo align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response text. These existing methods have two key limitations. First, the users rarely provide explicit feedback for LLM responses, which makes the high-quality preference annotation expensive to collect. Second, the methods do not leverage implicit human feedback, which has proven vital to the economic moats of Internet giants. To quantify the value of implicit feedback, we build a new dataset called IFLLM, which collects 1336 multi-turn questions from the 59 Mechanical Turk workers, their mouse trajectories, and eye gazing points to the LLMs' responses from their webcams. IFLLM shows that the users have very diverse types of gazing behavior and mouse trajectories. Our reward model based on the implicit user feedback boosts the accuracy of the text-based reward model from 55% to 64% and nearly triples the relative response quality improvements after applying the DPO to eight LLMs, demonstrating the value of implicit feedback in the wild. Our data collection website, dataset, and codes can be found at https://github.com/themehulpatwari/llm-implicit-feedback/.