# On the Role of Citations in Preference Data

arXiv: https://arxiv.org/abs/2608.21376 · HTML: https://mlsanity.com/paper/2608.21376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 65 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 39)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [One Token to Fool LLM-as-a-Judge](https://mlsanity.com/paper/2507.08794/) (2025)
- [ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics](https://mlsanity.com/paper/2509.00496/) (2025)
- [Training Language Models to Generate Text with Citations via Fine-grained Rewards](https://mlsanity.com/paper/2402.04315/) (2024)
- [Search Arena: Analyzing Search-Augmented LLMs](https://mlsanity.com/paper/2506.05334/) (2025)
- [Copilot Arena: A Platform for Code LLM Evaluation in the Wild](https://mlsanity.com/paper/2502.09328/) (2025)
- [What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data](https://mlsanity.com/paper/2510.26202/) (2025)
- [reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs](https://mlsanity.com/paper/2503.11751/) (2025)
- [Ai2 Scholar QA: Organized Literature Synthesis with Attribution](https://mlsanity.com/paper/2504.10861/) (2025)
- [RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment](https://mlsanity.com/paper/2412.13746/) (2024)
- [Explaining Datasets in Words: Statistical Models with Natural Language Parameters](https://mlsanity.com/paper/2409.08466/) (2024)
- [Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias](https://mlsanity.com/paper/2405.15739/) (2024)
- [MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs](https://mlsanity.com/paper/2505.24858/) (2025)
- [PrefPalette: Personalized Preference Modeling with Latent Attributes](https://mlsanity.com/paper/2507.13541/) (2025)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [Dialect-robust Evaluation of Generated Text](https://mlsanity.com/paper/2211.00922/) (2022)
- [Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models](https://mlsanity.com/paper/2506.05339/) (2025)
- [Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking](https://mlsanity.com/paper/2509.11353/) (2025)

## Abstract (arXiv)

Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model hallucination and as a means for users to verify the credibility of model outputs. Yet, it is unclear how humans and LLMs evaluate citations when comparing outputs, a process central to reward modeling and modern LLM post-training. This paper studies the role of citations in the preferences of human judges and four open-source LLMs within the context of scientific question answering, leveraging mixed effects models to investigate the influence of citations on pairwise judgments. Among our key findings are (1) that humans prefer more diverse citations but fewer overall, and (2) that LLMs show some citation-related preferences compared to humans, despite lacking access to the sources, but these preferences depend on the data and specific models. We further discuss the implications of our findings for preference data collection.