Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning
cs.AI
Submitted: 2026-06-29
Updated: 2026-10-31
Terminology
Sources
- Qwen3-VL Technical Report
- REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection
- Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
- Cognitive Foundations for Reasoning and Their Manifestation in LLMs
- PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment
- Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning
- Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
- Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
- EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models
- A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models
- Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
- Reinforcement Learning for Large Model: A Survey
- DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
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