# Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling

arXiv: https://arxiv.org/abs/2604.13271 · HTML: https://mlsanity.com/paper/2604.13271/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge](https://mlsanity.com/paper/2310.15051/) (2023)
- [TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models](https://mlsanity.com/paper/2407.09424/) (2024)
- [A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions](https://mlsanity.com/paper/2412.19823/) (2024)
- [ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks](https://mlsanity.com/paper/2407.06245/) (2024)
- [TeleChat Technical Report](https://mlsanity.com/paper/2401.03804/) (2024)
- [NetGPT: A Native-AI Network Architecture Beyond Provisioning Personalized Generative Services](https://mlsanity.com/paper/2307.06148/) (2023)
- [ORANSight-2.0: Foundational LLMs for O-RAN](https://mlsanity.com/paper/2503.05200/) (2025)
- [Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs](https://mlsanity.com/paper/2505.23845/) (2025)
- [Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration](https://mlsanity.com/paper/2404.15869/) (2024)
- [Calibration of Neural Networks](https://mlsanity.com/paper/2303.10761/) (2023)
- [AI5GTest: AI-Driven Specification-Aware Automated Testing and Validation of 5G O-RAN Components](https://mlsanity.com/paper/2506.10111/) (2025)
- [Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations](https://mlsanity.com/paper/2601.08064/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly applied to complex telecommunications tasks, including 3GPP specification analysis and O-RAN network troubleshooting. However, a critical limitation remains: LLM-generated confidence scores are often biased and unreliable, frequently exhibiting systematic overconfidence. This lack of trustworthy self-assessment makes it difficult to verify model outputs and safely rely on them in practice. In this paper, we study confidence calibration in telecom-domain LLMs using the representative Gemma-3 model family (4B, 12B, and 27B parameters), evaluated on TeleQnA, ORANBench, and srsRANBench. We show that standard single-pass, verbalized confidence estimates fail to reflect true correctness, often assigning high confidence to incorrect predictions. To address this, we propose a novel Twin-Pass Chain of Thought (CoT)-Ensembling methodology for improving confidence estimation by leveraging multiple independent reasoning evaluations and aggregating their assessments into a calibrated confidence score. Our approach reduces Expected Calibration Error (ECE) by up to 88% across benchmarks, significantly improving the reliability of model self-assessment. These results highlight the limitations of current confidence estimation practices and demonstrate a practical path toward more trustworthy evaluation of LLM outputs in telecommunications.