HILDIF: Interactive Debugging of NLI Models Using Influence Functions
Biases and artifacts in training data can cause unwelcome behavior in text classifiers (such as shallow pattern matching), leading to lack of generalizability. One solution to this problem is to include users in the loop and leverage their feedback to improve models. We propose a novel explanatory debugging pipeline called HILDIF, enabling humans to improve deep text classifiers using influence functions as an explanation method. We experiment on the Natural Language Inference (NLI) task, showing that HILDIF can effectively alleviate artifact problems in fine-tuned BERT models and result in increased model generalizability.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language InferenceSimilar Papers 제목 키워드 기반
Complaint-driven Training Data Debugging for Query 2.0
As the need for machine learning (ML) increases rapidly across all industry sectors, there is a significant interest among commercial database providers to support "Query 2.0", which integrates model inference into SQL q…
Understanding Black-box Predictions via Influence Functions
How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to…
Interactive Debugging and Steering of Multi-Agent AI Systems
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative inter…
AI Agentdebug-gym: A Text-Based Environment for Interactive Debugging
Large Language Models (LLMs) are increasingly relied upon for coding tasks, yet in most scenarios it is assumed that all relevant information can be either accessed in context or matches their training data. We posit tha…
Interactive Visualization for Debugging RL
Visualization tools for supervised learning allow users to interpret, introspect, and gain an intuition for the successes and failures of their models. While reinforcement learning practitioners ask many of the same ques…