Search Arena: Analyzing Search-Augmented LLMs

• URL: http://arxiv.org/abs/2506.05334v1
• Date: Thu, 05 Jun 2025 17:59:26 GMT
• Title: Search Arena: Analyzing Search-Augmented LLMs
• Authors: Mihran Miroyan, Tsung-Han Wu, Logan King, Tianle Li, Jiayi Pan, Xinyan Hu, Wei-Lin Chiang, Anastasios N. Angelopoulos, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez,
• Abstract summary: We introduce Search Arena, a crowd-sourced, large-scale, human-preference dataset of over 24,000 paired multi-turn user interactions.<n>The dataset spans diverse intents and languages, and contains full system traces with around 12,000 human preference votes.<n>Our analysis reveals that user preferences are influenced by the number of citations, even when the cited content does not directly support the attributed claims.
• Score: 61.28673331156436
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Search-augmented language models combine web search with Large Language Models (LLMs) to improve response groundedness and freshness. However, analyzing these systems remains challenging: existing datasets are limited in scale and narrow in scope, often constrained to static, single-turn, fact-checking questions. In this work, we introduce Search Arena, a crowd-sourced, large-scale, human-preference dataset of over 24,000 paired multi-turn user interactions with search-augmented LLMs. The dataset spans diverse intents and languages, and contains full system traces with around 12,000 human preference votes. Our analysis reveals that user preferences are influenced by the number of citations, even when the cited content does not directly support the attributed claims, uncovering a gap between perceived and actual credibility. Furthermore, user preferences vary across cited sources, revealing that community-driven platforms are generally preferred and static encyclopedic sources are not always appropriate and reliable. To assess performance across different settings, we conduct cross-arena analyses by testing search-augmented LLMs in a general-purpose chat environment and conventional LLMs in search-intensive settings. We find that web search does not degrade and may even improve performance in non-search settings; however, the quality in search settings is significantly affected if solely relying on the model's parametric knowledge. We open-sourced the dataset to support future research in this direction. Our dataset and code are available at: https://github.com/lmarena/search-arena.

Related papers

• Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses [11.330846631937671]
  We explore the application of large language models (LLMs) to empower domain experts in integrating large, heterogeneous, and noisy urban spatial datasets.<n>We show that while LLMs exhibit spatial reasoning capabilities, they struggle to connect the macro-scale environment with the relevant computational geometry tasks.<n>We then adapt a review-and-refine method, which proves remarkably effective in correcting erroneous initial responses while preserving accurate responses.
  arXiv  Detail & Related papers  (2025-08-07T03:44:20Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• Leveraging LLMs to Enable Natural Language Search on Go-to-market Platforms [0.23301643766310368]
  We implement and evaluate a solution for the Zoominfo product for sellers, which prompts the Large Language Models with natural language. The intermediary search fields offer numerous advantages for each query, including the elimination of syntax errors. Comprehensive experiments with closed, open source, and fine-tuned LLM models were conducted to demonstrate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-11-07T03:58:38Z)
• Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs [50.40165119718928]
  LongPiBench is a benchmark designed to assess positional bias involving multiple pieces of relevant information.<n>These experiments reveal that while most current models are robust against the "lost in the middle" issue, there exist significant biases related to the spacing of relevant information pieces.
  arXiv  Detail & Related papers  (2024-10-18T17:41:19Z)
• CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval [52.134133938779776]
  We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn.
  arXiv  Detail & Related papers  (2024-04-28T18:21:31Z)
• Factuality of Large Language Models: A Survey [29.557596701431827]
  We critically analyze existing work with the aim to identify the major challenges and their associated causes. We analyze the obstacles to automated factuality evaluation for open-ended text generation.
  arXiv  Detail & Related papers  (2024-02-04T09:36:31Z)
• Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
  We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy.<n>We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound.<n>Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
  arXiv  Detail & Related papers  (2023-12-01T00:54:02Z)
• ROBBIE: Robust Bias Evaluation of Large Generative Language Models [27.864027322486375]
  Different prompt-based datasets can be used to measure social bias across multiple text domains and demographic axes. We compare 6 different prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative LLMs. We conduct a comprehensive study of how well 3 bias/toxicity mitigation techniques perform across our suite of measurements.
  arXiv  Detail & Related papers  (2023-11-29T23:03:04Z)
• Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion [16.563311988191636]
  We construct an entity-centric knowledge store for each user based on their search and browsing activities on the web. This knowledge store is light-weight, since it only produces user-specific aggregate projections of interests and knowledge onto public knowledge graphs.
  arXiv  Detail & Related papers  (2023-11-10T01:18:47Z)
• Exposing Query Identification for Search Transparency [69.06545074617685]
  We explore the feasibility of approximate exposing query identification (EQI) as a retrieval task by reversing the role of queries and documents in two classes of search systems. We derive an evaluation metric to measure the quality of a ranking of exposing queries, as well as conducting an empirical analysis focusing on various practical aspects of approximate EQI.
  arXiv  Detail & Related papers  (2021-10-14T20:19:27Z)

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.