Investigating LLM Variability in Personalized Conversational Information Retrieval

• URL: http://arxiv.org/abs/2510.03795v1
• Date: Sat, 04 Oct 2025 12:13:19 GMT
• Title: Investigating LLM Variability in Personalized Conversational Information Retrieval
• Authors: Simon Lupart, Daniël van Dijk, Eric Langezaal, Ian van Dort, Mohammad Aliannejadi,
• Abstract summary: Mo et al. explored several strategies for incorporating Personal Textual Knowledge Bases (PTKB) into Large Language Models (LLMs)<n>We apply the original methods to a new TREC iKAT 2024 dataset and evaluate a diverse range of models, including Llama (1B-70B), Qwen-7B, GPT-4o-mini.<n>Our results show that human-selected PTKBs consistently enhance retrieval performance, while LLM-based selection methods do not reliably outperform manual choices.
• Score: 14.220276130333849
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personalized Conversational Information Retrieval (CIR) has seen rapid progress in recent years, driven by the development of Large Language Models (LLMs). Personalized CIR aims to enhance document retrieval by leveraging user-specific information, such as preferences, knowledge, or constraints, to tailor responses to individual needs. A key resource for this task is the TREC iKAT 2023 dataset, designed to evaluate personalization in CIR pipelines. Building on this resource, Mo et al. explored several strategies for incorporating Personal Textual Knowledge Bases (PTKB) into LLM-based query reformulation. Their findings suggested that personalization from PTKBs could be detrimental and that human annotations were often noisy. However, these conclusions were based on single-run experiments using the GPT-3.5 Turbo model, raising concerns about output variability and repeatability. In this reproducibility study, we rigorously reproduce and extend their work, focusing on LLM output variability and model generalization. We apply the original methods to the new TREC iKAT 2024 dataset and evaluate a diverse range of models, including Llama (1B-70B), Qwen-7B, GPT-4o-mini. Our results show that human-selected PTKBs consistently enhance retrieval performance, while LLM-based selection methods do not reliably outperform manual choices. We further compare variance across datasets and observe higher variability on iKAT than on CAsT, highlighting the challenges of evaluating personalized CIR. Notably, recall-oriented metrics exhibit lower variance than precision-oriented ones, a critical insight for first-stage retrievers. Finally, we underscore the need for multi-run evaluations and variance reporting when assessing LLM-based CIR systems. By broadening evaluation across models, datasets, and metrics, our study contributes to more robust and generalizable practices for personalized CIR.

Related papers

• The LLM Data Auditor: A Metric-oriented Survey on Quality and Trustworthiness in Evaluating Synthetic Data [25.926467401802046]
  Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities.<n>We propose a framework for evaluating synthetic data from two dimensions: quality and trustworthiness.
  arXiv  Detail & Related papers  (2026-01-25T06:40:25Z)
• How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models [24.90505576458548]
  We evaluate state-of-the-art reranking methods, including large language model (LLM)-based, lightweight contextual, and zero-shot approaches.<n>Our primary goal is to determine, through controlled and fair comparisons, whether a performance disparity exists between LLM-based rerankers and their lightweight counterparts.
  arXiv  Detail & Related papers  (2025-08-22T19:30:04Z)
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models [83.8639566087953]
  We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components.<n>DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted, progressively improving RAG components.<n>Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-05T23:54:53Z)
• Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution [66.11004226578771]
  Existing robust benchmark datasets have two key limitations.<n>They generate only a limited range of perturbations for a single Information Extraction (IE) task.<n>Considering the powerful generation capabilities of Large Language Models (LLMs), we introduce a new benchmark dataset for Robust UIE, called RUIE-Bench.<n>We show that training with only textbf15% of the data leads to an average textbf7.5% relative performance improvement across three IE tasks.
  arXiv  Detail & Related papers  (2025-03-05T05:39:29Z)
• Revisiting BPR: A Replicability Study of a Common Recommender System Baseline [78.00363373925758]
  We study the features of the BPR model, indicating their impact on its performance, and investigate open-source BPR implementations. Our analysis reveals inconsistencies between these implementations and the original BPR paper, leading to a significant decrease in performance of up to 50% for specific implementations. We show that the BPR model can achieve performance levels close to state-of-the-art methods on the top-n recommendation tasks and even outperform them on specific datasets.
  arXiv  Detail & Related papers  (2024-09-21T18:39:53Z)
• CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [58.57987316300529]
  Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks.<n>To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets.<n>We propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
  arXiv  Detail & Related papers  (2024-07-02T16:31:37Z)
• Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks [0.0]
  Relation Extraction (RE) is crucial for converting unstructured data into structured formats like Knowledge Graphs (KGs) Recent studies leveraging pre-trained language models (PLMs) have shown significant success in this area. This work explores the performance of fine-tuned LLMs and their integration into the Retrieval Augmented-based (RAG) RE approach.
  arXiv  Detail & Related papers  (2024-06-20T21:27:57Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Adapting LLMs for Efficient, Personalized Information Retrieval: Methods and Implications [0.7832189413179361]
  Large Language Models (LLMs) excel in comprehending and generating human-like text. This paper explores strategies for integrating Language Models (LLMs) with Information Retrieval (IR) systems.
  arXiv  Detail & Related papers  (2023-11-21T02:01:01Z)
• From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
  We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
  arXiv  Detail & Related papers  (2023-08-23T09:45:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.