# Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs

arXiv: https://arxiv.org/abs/2406.11278 · HTML: https://mlsanity.com/paper/2406.11278/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Conditional Image Generation with PixelCNN Decoders](https://mlsanity.com/paper/1606.05328/) (2016)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency](https://mlsanity.com/paper/2311.01740/) (2023)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Calibrating Large Language Models with Sample Consistency](https://mlsanity.com/paper/2402.13904/) (2024)
- [Calibrating Large Language Models Using Their Generations Only](https://mlsanity.com/paper/2403.05973/) (2024)
- [Mitigating LLM Hallucinations via Conformal Abstention](https://mlsanity.com/paper/2405.01563/) (2024)
- [Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method](https://mlsanity.com/paper/2310.17918/) (2023)
- [MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs](https://mlsanity.com/paper/2402.11756/) (2024)
- [Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection](https://mlsanity.com/paper/2403.09972/) (2024)
- [Conformal Autoregressive Generation: Beam Search with Coverage Guarantees](https://mlsanity.com/paper/2309.03797/) (2023)
- [Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts](https://mlsanity.com/paper/2406.05569/) (2024)

## Built on by (most cited first, 23 of 23)

- [Leveraging Uncertainty Estimation for Efficient LLM Routing](https://mlsanity.com/paper/2502.11021/) (2025)
- [From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered](https://mlsanity.com/paper/2506.07461/) (2025)
- [Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure](https://mlsanity.com/paper/2412.15176/) (2024)
- [Reconsidering LLM Uncertainty Estimation Methods in the Wild](https://mlsanity.com/paper/2506.01114/) (2025)
- [Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions](https://mlsanity.com/paper/2510.12040/) (2025)
- [Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering](https://mlsanity.com/paper/2510.02671/) (2025)
- [Uncertainty Quantification for Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2510.11483/) (2025)
- [TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs](https://mlsanity.com/paper/2507.08203/) (2025)
- [Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making](https://mlsanity.com/paper/2508.15926/) (2025)
- [Semantic Self-Distillation for Language Model Uncertainty](https://mlsanity.com/paper/2602.04577/) (2026)
- [Towards Harmonized Uncertainty Estimation for Large Language Models](https://mlsanity.com/paper/2505.19073/) (2025)
- [HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models](https://mlsanity.com/paper/2510.22171/) (2025)
- [Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning](https://mlsanity.com/paper/2601.13284/) (2026)
- [Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA](https://mlsanity.com/paper/2606.27023/) (2026)
- [Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge](https://mlsanity.com/paper/2411.09689/) (2024)
- [SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models](https://mlsanity.com/paper/2510.13836/) (2025)
- [HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering](https://mlsanity.com/paper/2512.24562/) (2025)
- [Probabilistic distances-based hallucination detection in LLMs with RAG](https://mlsanity.com/paper/2506.09886/) (2025)
- [Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements](https://mlsanity.com/paper/2506.01089/) (2025)
- [Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning](https://mlsanity.com/paper/2604.08974/) (2026)
- [Knowledge Dependency Estimation for Reliable Question Answering](https://mlsanity.com/paper/2605.28047/) (2026)
- [Uncertainty Quantification for Multimodal Retrieval Augmented Generation](https://mlsanity.com/paper/2605.29956/) (2026)
- [TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration](https://mlsanity.com/paper/2609.35387/) (2026)

## Abstract (arXiv)

Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize token probabilities to assess uncertainty, aggregating multiple token probabilities into a single UE score using a scoring function. Existing scoring functions for probability-based UE, such as length-normalized scoring and semantic contribution-based weighting, are designed to solve certain aspects of the problem but exhibit limitations, including the inability to handle biased probabilities and complex semantic dependencies between tokens. To address these issues, in this work, we propose Learnable Response Scoring (LARS) function, a novel scoring function that leverages supervised data to capture complex dependencies between tokens and probabilities, thereby producing more reliable and calibrated response scores in computing the uncertainty of LLM generations. Our comprehensive experiments across question-answering and arithmetical reasoning tasks with various datasets demonstrate that LARS significantly outperforms existing scoring functions, achieving improvements of up to 16% AUROC score.