# Calibrating Long-form Generations from Large Language Models

arXiv: https://arxiv.org/abs/2402.06544 · HTML: https://mlsanity.com/paper/2402.06544/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 30 of 35)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Reducing conversational agents' overconfidence through linguistic calibration](https://mlsanity.com/paper/2012.14983/) (2020)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)

## Built on by (most cited first, 30 of 32)

- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey](https://mlsanity.com/paper/2503.15850/) (2025)
- [Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents](https://mlsanity.com/paper/2505.22655/) (2025)
- [A Survey on the Honesty of Large Language Models](https://mlsanity.com/paper/2409.18786/) (2024)
- [Long-Form Answers to Visual Questions from Blind and Low Vision People](https://mlsanity.com/paper/2408.06303/) (2024)
- [LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations](https://mlsanity.com/paper/2505.23912/) (2025)
- [On Subjective Uncertainty Quantification and Calibration in Natural Language Generation](https://mlsanity.com/paper/2406.05213/) (2024)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards](https://mlsanity.com/paper/2602.21158/) (2026)
- [FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees](https://mlsanity.com/paper/2411.02603/) (2024)
- [Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models](https://mlsanity.com/paper/2504.02902/) (2025)
- [LLMs can learn self-restraint through iterative self-reflection](https://mlsanity.com/paper/2405.13022/) (2024)
- [Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation](https://mlsanity.com/paper/2604.02543/) (2026)
- [Logits are All We Need to Adapt Closed Models](https://mlsanity.com/paper/2502.06806/) (2025)
- [Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs](https://mlsanity.com/paper/2510.05987/) (2025)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality](https://mlsanity.com/paper/2507.08371/) (2025)
- [Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study](https://mlsanity.com/paper/2602.17431/) (2026)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.20825/) (2025)
- [Certainty robustness: Evaluating LLM stability under self-challenging prompts](https://mlsanity.com/paper/2603.03330/) (2026)
- [Retrieval-Augmented Linguistic Calibration](https://mlsanity.com/paper/2605.19344/) (2026)
- [EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering](https://mlsanity.com/paper/2501.12746/) (2025)
- [Atomic Consistency Preference Optimization for Long-Form Question Answering](https://mlsanity.com/paper/2505.09039/) (2025)
- [Trusted Uncertainty in Large Language Models: A Unified Framework for Confidence Calibration and Risk-Controlled Refusal](https://mlsanity.com/paper/2509.01455/) (2025)
- [Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models](https://mlsanity.com/paper/2603.19262/) (2026)
- [Gauging Overprecision in LLMs: An Empirical Study](https://mlsanity.com/paper/2504.12098/) (2025)
- [Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration](https://mlsanity.com/paper/2603.02760/) (2026)
- [Task-Aware Calibration: Provably Optimal Decoding in LLMs](https://mlsanity.com/paper/2605.10202/) (2026)
- [On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study](https://mlsanity.com/paper/2608.22089/) (2026)

## Abstract (arXiv)

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods and calibration metrics typically rely on a binary true/false assessment of response correctness. This approach does not apply to long-form generation, where an answer can be partially correct. Addressing this gap, we introduce a unified calibration framework, in which both the correctness of the LLMs' responses and their associated confidence levels are treated as distributions across a range of scores. Within this framework, we develop three metrics to precisely evaluate LLM calibration and further propose two confidence elicitation methods based on self-consistency and self-evaluation. Our experiments, which include long-form QA and summarization tasks, demonstrate that larger models don't necessarily guarantee better calibration, that calibration performance is found to be metric-dependent, and that self-consistency methods excel in factoid datasets. We also find that calibration can be enhanced through techniques such as fine-tuning, integrating relevant source documents, scaling the temperature, and combining self-consistency with self-evaluation. Lastly, we showcase a practical application of our system: selecting and cascading open-source models and ChatGPT to optimize correctness given a limited API budget. This research not only challenges existing notions of LLM calibration but also offers practical methodologies for improving trustworthiness in long-form generation.