Cover Image

Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Shiting, Zhao, Zijian, Chen, Jinsong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

First Token Probability Guided RAG for Telecom Question Answering
by: Chen, Tingwei, et al.
Published: (2025)

Confidence-guided Refinement Reasoning for Zero-shot Question Answering
by: Jang, Youwon, et al.
Published: (2025)

CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering
by: Elshaer, Ziad, et al.
Published: (2025)

Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments
by: Chakravarty, Abhirup, et al.
Published: (2025)

Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
by: Lin, Zhen, et al.
Published: (2024)

Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
by: Chen, Yingjian, et al.
Published: (2025)

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
by: Bhattacharyya, Sree, et al.
Published: (2026)

Graph Neural Network Enhanced Retrieval for Question Answering of LLMs
by: Li, Zijian, et al.
Published: (2024)

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
by: Zhuang, Ziyuan, et al.
Published: (2024)

Augmenting Question Answering with A Hybrid RAG Approach
by: Yang, Tianyi, et al.
Published: (2026)

GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
by: Luo, Jinchang, et al.
Published: (2025)

Confidence Improves Self-Consistency in LLMs
by: Taubenfeld, Amir, et al.
Published: (2025)

From RAG to Agentic RAG for Faithful Islamic Question Answering
by: Bhatia, Gagan, et al.
Published: (2026)

SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering
by: Zhong, Kezhen, et al.
Published: (2025)

Credible Plan-Driven RAG Method for Multi-Hop Question Answering
by: Zhang, Ningning, et al.
Published: (2025)

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding
by: Liu, Yichen, et al.
Published: (2022)

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
by: Pathak, Manas, et al.
Published: (2026)

Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering
by: Yang, Hongyu, et al.
Published: (2024)

CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering
by: Wiratunga, Nirmalie, et al.
Published: (2024)

Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
by: Zhang, Yichi, et al.
Published: (2023)

Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks
by: Song, Yiliang, et al.
Published: (2026)

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
by: Balkır, Esma, et al.
Published: (2026)

Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
by: Wang, Pei, et al.
Published: (2024)

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
by: Thompson, Travis, et al.
Published: (2025)

CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
by: Yang, Hao, et al.
Published: (2026)

RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering
by: Um, Kaehyun, et al.
Published: (2026)

Learning to Route LLMs with Confidence Tokens
by: Chuang, Yu-Neng, et al.
Published: (2024)

Confidence is Not Competence
by: Sanyal, Debdeep, et al.
Published: (2025)

Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
by: Sturm, Jakob, et al.
Published: (2026)

Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering
by: Wang, Yubo, et al.
Published: (2023)

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
by: Fu, Tairan, et al.
Published: (2025)

Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics
by: Flores, Lorenzo Jaime Yu, et al.
Published: (2025)

Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS
by: Alan, Ahmet Yusuf, et al.
Published: (2024)

How do LLMs Compute Verbal Confidence
by: Kumaran, Dharshan, et al.
Published: (2026)

Agentic Confidence Calibration
by: Zhang, Jiaxin, et al.
Published: (2026)

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
by: Zhang, Rongyang, et al.
Published: (2025)

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning
by: Cai, Hongyi, et al.
Published: (2025)

Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering
by: Yang, Wanqi, et al.
Published: (2024)

NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering
by: Cao, Ruisheng, et al.
Published: (2025)

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward
by: An, Hao, et al.
Published: (2025)