Multimodal Abstention That Preserves Acquired Correct Answers
cs.AI, cs.CV, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/ModeLiberaL/ReFrain
Terminology
Sources
- Conformal Risk Control
- Qwen2.5-VL Technical Report
- MUSCLE: A Model Update Strategy for Compatible LLM Evolution
- Dr. No: Feature Steering for Abstention in Vision-Language Models
- From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models
- A Diagram Is Worth A Dozen Images
- Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions
- FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
- Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)
- Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering
- Backward-Compatible Prediction Updates: A Probabilistic Approach
- CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering
- Two Axes of LLM Abstention: Answer Correctness and Question Answerability
- LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
- Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
- Variational Visual Question Answering for Uncertainty-Aware Selective Prediction
- VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
- Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
- Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents