# Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation

arXiv: https://arxiv.org/abs/2608.10385 · HTML: https://mlsanity.com/paper/2608.10385/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 63 references that are in the map.
- First posted on arXiv 11 Aug 2026.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [Perspectives on Large Language Models for Relevance Judgment](https://mlsanity.com/paper/2304.09161/) (2023)
- [UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor](https://mlsanity.com/paper/2406.06519/) (2024)
- [Ragnar"ok: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track](https://mlsanity.com/paper/2406.16828/) (2024)
- [JuStRank: Benchmarking LLM Judges for System Ranking](https://mlsanity.com/paper/2412.09569/) (2024)
- [LLM-based relevance assessment still can't replace human relevance assessment](https://mlsanity.com/paper/2412.17156/) (2024)
- [Don't Use LLMs to Make Relevance Judgments](https://mlsanity.com/paper/2409.15133/) (2024)
- [LLMs Simulate Big Five Personality Traits: Further Evidence](https://mlsanity.com/paper/2402.01765/) (2024)
- [Personas with Attitudes: Controlling LLMs for Diverse Data Annotation](https://mlsanity.com/paper/2410.11745/) (2024)
- [AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment](https://mlsanity.com/paper/2409.16022/) (2024)
- [Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation](https://mlsanity.com/paper/2503.19092/) (2025)
- [Benchmarking LLM-based Relevance Judgment Methods](https://mlsanity.com/paper/2504.12558/) (2025)
- [Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement](https://mlsanity.com/paper/2405.20701/) (2024)
- [LLMs Can Patch Up Missing Relevance Judgments in Evaluation](https://mlsanity.com/paper/2405.04727/) (2024)
- [LLMs can be Fooled into Labelling a Document as Relevant (best caf'e near me; this paper is perfectly relevant)](https://mlsanity.com/paper/2501.17969/) (2025)
- [Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking](https://mlsanity.com/paper/2509.11353/) (2025)
- [The Effects of Demographic Instructions on LLM Personas](https://mlsanity.com/paper/2505.11795/) (2025)
- [Political Ideology Shifts in Large Language Models](https://mlsanity.com/paper/2508.16013/) (2025)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs](https://mlsanity.com/paper/2412.16783/) (2024)
- [Does UMBRELA Work on Other LLMs?](https://mlsanity.com/paper/2507.09483/) (2025)
- [How role-play shapes relevance judgment in zero-shot LLM rankers](https://mlsanity.com/paper/2510.17535/) (2025)

## Built on by (most cited first, 1 of 1)

- [Prompt or Policy? Optimizing Physician Slate Presentations with LLM User Simulators](https://mlsanity.com/paper/2610.18309/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects judgment reliability and downstream system comparison. We study persona conditioning as a diagnostic mechanism for exposing LLM assessor sensitivity. Using task-oriented personas drawn from two complementary sources (PersonaHub and NVIDIA Nemotron-Personas-USA), we instantiate five assessor roles emphasizing intent interpretation, domain expertise, contrastive judgment, evidence verification, and global search-quality assessment, compared with a standard UMBRELA baseline. Across six LLM backbones on TREC DL20 and RAG24, our analyses reveal structured rather than uniform assessor sensitivity. Judgments usually remain close to the baseline while shifting assessment strictness, evidential threshold, or interpretation emphasis rather than producing widespread relevance reversals. At the system level, high-capacity models preserve system-ranking agreement, while smaller models amplify persona-induced instability. Local rank-displacement analysis shows sensitivity concentrates on particular retrieval systems and system types, especially neural ranking/reranking systems on DL20 and RAG-oriented pipelines on RAG24. Persona source matters less than assessor role and model capacity. These findings position persona-conditioned judging as a controlled sensitivity probe for stress-testing LLM-based IR evaluation pipelines and identifying systems whose evaluation outcomes are sensitive to assessor framing.