# "Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?

arXiv: https://arxiv.org/abs/2406.17600 · HTML: https://mlsanity.com/paper/2406.17600/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 30 of 32)

- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [What Can We Learn from Collective Human Opinions on Natural Language Inference Data?](https://mlsanity.com/paper/2010.03532/) (2020)
- [Toward a Perspectivist Turn in Ground Truthing for Predictive Computing](https://mlsanity.com/paper/2109.04270/) (2021)
- [Stop Measuring Calibration When Humans Disagree](https://mlsanity.com/paper/2210.16133/) (2022)
- [SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)](https://mlsanity.com/paper/2304.14803/) (2023)
- [VariErr NLI: Separating Annotation Error from Human Label Variation](https://mlsanity.com/paper/2403.01931/) (2024)
- [Can Large Language Models Capture Dissenting Human Voices?](https://mlsanity.com/paper/2305.13788/) (2023)
- [Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning](https://mlsanity.com/paper/2104.08676/) (2021)
- [The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation](https://mlsanity.com/paper/2405.01299/) (2024)
- [Making Large Language Models Better Data Creators](https://mlsanity.com/paper/2310.20111/) (2023)
- [Ecologically Valid Explanations for Label Variation in NLI](https://mlsanity.com/paper/2310.13850/) (2023)

## Built on by (most cited first, 17 of 17)

- [Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge](https://mlsanity.com/paper/2410.03775/) (2024)
- [Always Tell Me The Odds: Fine-grained Conditional Probability Estimation](https://mlsanity.com/paper/2505.01595/) (2025)
- [Training and Evaluating with Human Label Variation: An Empirical Study](https://mlsanity.com/paper/2502.01891/) (2025)
- [Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models](https://mlsanity.com/paper/2510.11586/) (2025)
- [Diversity Boosts AI-Generated Text Detection](https://mlsanity.com/paper/2509.18880/) (2025)
- [Understanding The Effect Of Temperature On Alignment With Human Opinions](https://mlsanity.com/paper/2411.10080/) (2024)
- [Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer](https://mlsanity.com/paper/2504.12589/) (2025)
- [LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference](https://mlsanity.com/paper/2505.22848/) (2025)
- [Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems](https://mlsanity.com/paper/2506.20209/) (2025)
- [Revisiting Active Learning under (Human) Label Variation](https://mlsanity.com/paper/2507.02593/) (2025)
- [From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set](https://mlsanity.com/paper/2411.15387/) (2024)
- [SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs](https://mlsanity.com/paper/2606.05376/) (2026)
- [Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization](https://mlsanity.com/paper/2605.28802/) (2026)
- [Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection](https://mlsanity.com/paper/2605.31563/) (2026)
- [EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI](https://mlsanity.com/paper/2511.08949/) (2025)
- [Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP](https://mlsanity.com/paper/2603.28351/) (2026)
- [Whose Ground Truth? Embracing Ambiguity in Human-Centered AI](https://mlsanity.com/paper/2610.10805/) (2026)

## Abstract (arXiv)

Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference (NLI) earlier approaches to capturing HLV involve either collecting annotations from many crowd workers to represent human judgment distribution (HJD) or use expert linguists to provide detailed explanations for their chosen labels. While the former method provides denser HJD information, obtaining it is resource-intensive. In contrast, the latter offers richer textual information but it is challenging to scale up to many human judges. Besides, large language models (LLMs) are increasingly used as evaluators ("LLM judges") but with mixed results, and few works aim to study HJDs. This study proposes to exploit LLMs to approximate HJDs using a small number of expert labels and explanations. Our experiments show that a few explanations significantly improve LLMs' ability to approximate HJDs with and without explicit labels, thereby providing a solution to scale up annotations for HJD. However, fine-tuning smaller soft-label aware models with the LLM-generated model judgment distributions (MJDs) presents partially inconsistent results: while similar in distance, their resulting fine-tuned models and visualized distributions differ substantially. We show the importance of complementing instance-level distance measures with a global-level shape metric and visualization to more effectively evaluate MJDs against human judgment distributions.