Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
cs.CL
Submitted: 2026-05-28
Updated: 2026-09-26
Terminology
Sources
- Learning to Reason for Factuality
- SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
- Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
- QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
- Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
- KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
- Measuring short-form factuality in large language models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering