TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues

• URL: http://arxiv.org/abs/2207.04154v1
• Date: Fri, 8 Jul 2022 23:42:56 GMT
• Title: TalkToModel: Understanding Machine Learning Models With Open Ended Dialogues
• Authors: Dylan Slack and Satyapriya Krishna and Himabindu Lakkaraju and Sameer Singh
• Abstract summary: TalkToModel is an open-ended dialogue system for understanding machine learning models. It comprises three key components: 1) a natural language interface for engaging in dialogues, 2) a dialogue engine that interprets natural language, and 3) an execution component that runs the operations and ensures explanations are accurate.
• Score: 45.25552547278378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have also become more complex, making them harder to understand. To this end, several techniques to explain model predictions have been proposed. However, practitioners struggle to leverage explanations because they often do not know which to use, how to interpret the results, and may have insufficient data science experience to obtain explanations. In addition, most current works focus on generating one-shot explanations and do not allow users to follow up and ask fine-grained questions about the explanations, which can be frustrating. In this work, we address these challenges by introducing TalkToModel: an open-ended dialogue system for understanding machine learning models. Specifically, TalkToModel comprises three key components: 1) a natural language interface for engaging in dialogues, making understanding ML models highly accessible, 2) a dialogue engine that adapts to any tabular model and dataset, interprets natural language, maps it to appropriate operations (e.g., feature importance explanations, counterfactual explanations, showing model errors), and generates text responses, and 3) an execution component that run the operations and ensures explanations are accurate. We carried out quantitative and human subject evaluations of TalkToModel. We found the system understands user questions on novel datasets and models with high accuracy, demonstrating the system's capacity to generalize to new situations. In human evaluations, 73% of healthcare workers (e.g., doctors and nurses) agreed they would use TalkToModel over baseline point-and-click systems, and 84.6% of ML graduate students agreed TalkToModel was easier to use.

Related papers

• InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations [8.833264791078825]
  We adapt the conversational explanation framework TalkToModel to the NLP domain, add new NLP-specific operations such as free-text rationalization. To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models. We conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability.
  arXiv  Detail & Related papers  (2023-10-09T10:27:26Z)
• Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering [124.16250115608604]
  We present Science Question Answering (SQA), a new benchmark that consists of 21k multimodal multiple choice questions with a diverse set of science topics and annotations of their answers with corresponding lectures and explanations. We show that SQA improves the question answering performance by 1.20% in few-shot GPT-3 and 3.99% in fine-tuned UnifiedQA. Our analysis further shows that language models, similar to humans, benefit from explanations to learn from fewer data and achieve the same performance with just 40% of the data.
  arXiv  Detail & Related papers  (2022-09-20T07:04:24Z)
• NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks [18.13793282306575]
  Natural language explanation (NLE) models aim at explaining the decision-making process of a black box system. We introduce NLX-GPT, a general, compact and faithful language model that can simultaneously predict an answer and explain it. We then address the problem of evaluating the explanations which can be in many times generic, data-biased and can come in several forms.
  arXiv  Detail & Related papers  (2022-03-09T22:57:15Z)
• Rethinking Explainability as a Dialogue: A Practitioner's Perspective [57.87089539718344]
  We ask doctors, healthcare professionals, and policymakers about their needs and desires for explanations. Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues. Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations.
  arXiv  Detail & Related papers  (2022-02-03T22:17:21Z)
• GreaseLM: Graph REASoning Enhanced Language Models for Question Answering [159.9645181522436]
  GreaseLM is a new model that fuses encoded representations from pretrained LMs and graph neural networks over multiple layers of modality interaction operations. We show that GreaseLM can more reliably answer questions that require reasoning over both situational constraints and structured knowledge, even outperforming models 8x larger.
  arXiv  Detail & Related papers  (2022-01-21T19:00:05Z)
• Reason first, then respond: Modular Generation for Knowledge-infused Dialogue [43.64093692715295]
  Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. We propose a modular model, Knowledge to Response, for incorporating knowledge into conversational agents. In detailed experiments, we find that such a model hallucinates less in knowledge-grounded dialogue tasks.
  arXiv  Detail & Related papers  (2021-11-09T15:29:43Z)
• When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data [84.87772675171412]
  We study the circumstances under which explanations of individual data points can improve modeling performance. We make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval.
  arXiv  Detail & Related papers  (2021-02-03T18:57:08Z)
• Fusing Context Into Knowledge Graph for Commonsense Reasoning [21.33294077354958]
  We propose to utilize external entity description to provide contextual information for graph entities. For the CommonsenseQA task, our model first extracts concepts from the question and choice, and then finds a related triple between these concepts. We achieve state-of-the-art results in the CommonsenseQA dataset with an accuracy of 80.7% (single model) and 83.3% (ensemble model) on the official leaderboard.
  arXiv  Detail & Related papers  (2020-12-09T00:57:49Z)
• An Information-Theoretic Approach to Personalized Explainable Machine Learning [92.53970625312665]
  We propose a simple probabilistic model for the predictions and user knowledge. We quantify the effect of an explanation by the conditional mutual information between the explanation and prediction.
  arXiv  Detail & Related papers  (2020-03-01T13:06:29Z)
• What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations [5.802346990263708]
  This study is the first to use a conversational system to collect the needs of human operators from the interactive and iterative dialogue explorations of a predictive model. We developed dr_ant to talk about machine learning model trained to predict survival odds on Titanic. Having collected a corpus of 1000+ dialogues, we analyse the most common types of questions that users would like to ask.
  arXiv  Detail & Related papers  (2020-02-07T15:59:49Z)

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.