What is a Good Question? Utility Estimation with LLM-based Simulations

• URL: http://arxiv.org/abs/2502.17383v1
• Date: Mon, 24 Feb 2025 18:08:41 GMT
• Title: What is a Good Question? Utility Estimation with LLM-based Simulations
• Authors: Dong-Ho Lee, Hyundong Cho, Jonathan May, Jay Pujara,
• Abstract summary: QUEST simulates a learning environment that enables the quantification of a question's utility.<n>We find that questions generated by models trained with rejection sampling based on question utility result in exam scores that are higher by at least 20%.
• Score: 37.87879572754863
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Asking questions is a fundamental aspect of learning that facilitates deeper understanding. However, characterizing and crafting questions that effectively improve learning remains elusive. To address this gap, we propose QUEST (Question Utility Estimation with Simulated Tests). QUEST simulates a learning environment that enables the quantification of a question's utility based on its direct impact on improving learning outcomes. Furthermore, we can identify high-utility questions and use them to fine-tune question generation models with rejection sampling. We find that questions generated by models trained with rejection sampling based on question utility result in exam scores that are higher by at least 20% than those from specialized prompting grounded on educational objectives literature and models fine-tuned with indirect measures of question quality, such as saliency and expected information gain.

Related papers

• Uncertainty Quantification in Retrieval Augmented Question Answering [57.05827081638329]
  We propose to quantify the uncertainty of a QA model via estimating the utility of the passages it is provided with. We train a lightweight neural model to predict passage utility for a target QA model and show that while simple information theoretic metrics can predict answer correctness up to a certain extent, our approach efficiently approximates or outperforms more expensive sampling-based methods.
  arXiv  Detail & Related papers  (2025-02-25T11:24:52Z)
• Knowledge Graphs are all you need: Leveraging KGs in Physics Question Answering [28.279969366096978]
  We introduce a pipeline aimed at enhancing model response quality for Question Answering tasks.<n>By employing LLMs to construct knowledge graphs that capture the internal logic of the questions, these graphs then guide the generation of subquestions.<n>Results show that sub-questions derived from knowledge graphs exhibit significantly improved fidelity to the original question's logic.
  arXiv  Detail & Related papers  (2024-12-06T22:25:23Z)
• AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs [53.6200736559742]
  AGENT-CQ consists of two stages: a generation stage and an evaluation stage. CrowdLLM simulates human crowdsourcing judgments to assess generated questions and answers. Experiments on the ClariQ dataset demonstrate CrowdLLM's effectiveness in evaluating question and answer quality.
  arXiv  Detail & Related papers  (2024-10-25T17:06:27Z)
• Crafting Interpretable Embeddings by Asking LLMs Questions [89.49960984640363]
  Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. We introduce question-answering embeddings (QA-Emb), embeddings where each feature represents an answer to a yes/no question asked to an LLM. We use QA-Emb to flexibly generate interpretable models for predicting fMRI voxel responses to language stimuli.
  arXiv  Detail & Related papers  (2024-05-26T22:30:29Z)
• You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments [37.03210795084276]
  We examine whether the current format of prompting Large Language Models elicits responses in a consistent and robust manner. Our experiments on 17 different LLMs reveal that even simple perturbations significantly downgrade a model's question-answering ability. Our results suggest that the currently widespread practice of prompting is insufficient to accurately and reliably capture model perceptions.
  arXiv  Detail & Related papers  (2023-11-16T09:50:53Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions [70.70725223310401]
  This work proposes a new method that utilizes semantically related questions, referred to as basic questions, acting as noise to evaluate the robustness of VQA models. The experimental results demonstrate that the proposed evaluation method effectively analyzes the robustness of VQA models.
  arXiv  Detail & Related papers  (2023-04-06T15:32:35Z)
• Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards [20.342580435464072]
  We introduce a reinforcement learning-based framework for abstractive question summarization. We propose two novel rewards obtained from the downstream tasks of (i) question-type identification and (ii) question-focus recognition. These rewards ensure the generation of semantically valid questions and encourage the inclusion of key medical entities/foci in the question summary.
  arXiv  Detail & Related papers  (2021-07-01T02:06:46Z)
• Introducing a framework to assess newly created questions with Natural Language Processing [3.364554138758565]
  We propose a framework to train and evaluate models for estimating the difficulty and discrimination of newly created Multiple Choice Questions. We implement one model using this framework and test it on a real-world dataset provided by CloudAcademy.
  arXiv  Detail & Related papers  (2020-04-28T13:57:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.