WildSEEK: Evaluating Language Models for Information-Seeking

• URL: http://arxiv.org/abs/2608.30683v1
• Date: Mon, 31 Aug 2026 12:25:10 GMT
• Title: WildSEEK: Evaluating Language Models for Information-Seeking
• Abstract summary: We introduce WildSEEK, a manually annotated dataset of 3k information-seeking queries from real user interactions.<n>We also present an evaluation framework for LLM-generated responses.<n>We find that over a third of information-seeking queries are high-risk and more often analytical.
• Score: 33.69574645182675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models are increasingly mediating information access to end users, urging a systematic evaluation of their responses for a fair and reliable information ecosystem. Existing evaluations, however, are often topic-specific or synthetic, limiting their ability to capture the complexity of "in the wild" information-seeking queries and the risks present in model responses. To address this gap, we introduce WildSEEK, a manually annotated dataset of 3k information-seeking queries from real user interactions, and an evaluation framework for LLM-generated responses. WildSEEK includes annotations for risk-sensitive domains (e.g. health and financial information), and distinguishes factoid queries from analytical queries which seek responses beyond facts. We train classifiers on WildSEEK to analyze more than 1.8M realistic user queries. We find that over a third of information-seeking queries are high-risk and more often analytical. Our findings show that LLM responses fail more often in four criteria: sycophantic behavior, overreliance, a default US-centric perspective, and poor handling of vulnerable populations -- with failure rates being mostly higher for analytical queries. By providing methods to monitor the reliability, safety, and fairness of LLM behavior, our dataset and evaluation framework offer an empirical foundation for the broader question of how these systems should behave as they take on a growing role in information access.

Related papers

• Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities [16.09389994769264]
  We introduce DataGovBench, a benchmark designed to evaluate Large Language Models in practical scenarios.<n> Comprehensive experiments with state-of-the-art LLMs reveal significant performance gaps across both tasks.<n>DataGovBench provides a challenging benchmark for advancing research on LLMs capable of both answering analytical queries and discovering insights from data.
  arXiv  Detail & Related papers  (2026-07-07T16:43:05Z)
• GISA: A Benchmark for General Information-Seeking Assistant [102.30831921333755]
  GISA is a benchmark for General Information-Seeking Assistants comprising 373 human-crafted queries.<n>It integrates both deep reasoning and broad information aggregation within unified tasks, and includes a live subset with periodically updated answers to resist memorization.<n>Experiments on mainstream LLMs and commercial search products reveal that even the best-performing model achieves only 19.30% exact match score.
  arXiv  Detail & Related papers  (2026-02-09T11:44:15Z)
• Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges [72.3356133063925]
  The paradigm of large language models (LLMs) as judges has emerged as a scalable solution, yet prior work primarily focuses on simple settings.<n>Our in-depth analysis offers crucial insights for improving the accuracy and verifiability of evaluation signals.
  arXiv  Detail & Related papers  (2025-09-03T15:48:33Z)
• Teaching Language Models To Gather Information Proactively [53.85419549904644]
  Large language models (LLMs) are increasingly expected to function as collaborative partners.<n>In this work, we introduce a new task paradigm: proactive information gathering.<n>We design a scalable framework that generates partially specified, real-world tasks, masking key information.<n>Within this setup, our core innovation is a reinforcement finetuning strategy that rewards questions that elicit genuinely new, implicit user information.
  arXiv  Detail & Related papers  (2025-07-28T23:50:09Z)
• VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL [11.830097026198308]
  Application systems using natural language interfaces to databases (NLIDBs) have democratized data analysis.<n>This has also brought forth an urgent challenge to help users who might use these systems without a background in statistical analysis.<n>We present VeriMinder, https://veriminder.ai, an interactive system for detecting and mitigating such analytical vulnerabilities.
  arXiv  Detail & Related papers  (2025-07-23T19:48:12Z)
• InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation [63.55258191625131]
  InfoDeepSeek is a new benchmark for assessing agentic information seeking in real-world, dynamic web environments.<n>We propose a systematic methodology for constructing challenging queries satisfying the criteria of determinacy, difficulty, and diversity.<n>We develop the first evaluation framework tailored to dynamic agentic information seeking, including fine-grained metrics about the accuracy, utility, and compactness of information seeking outcomes.
  arXiv  Detail & Related papers  (2025-05-21T14:44:40Z)
• LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights [12.424610893030353]
  Large Language Models (LLMs) are emerging as transformative tools for software vulnerability detection.<n>This paper provides a detailed survey of LLMs in vulnerability detection.<n>We address challenges such as cross-language vulnerability detection, multimodal data integration, and repository-level analysis.
  arXiv  Detail & Related papers  (2025-02-10T21:33:38Z)
• Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation [19.543102037001134]
  Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowledge corpus provides a tangible solution to these problems. RAG generation quality is highly dependent on the relevance between a user's query and the retrieved documents.
  arXiv  Detail & Related papers  (2024-10-10T19:14:55Z)
• NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities [51.07379913779232]
  NeedleBench is a framework for assessing retrieval and reasoning performance in long-context tasks.<n>It embeds key data points at varying depths to rigorously test model capabilities.<n>Our experiments reveal that reasoning models like Deep-R1 and OpenAI's o3 struggle with continuous retrieval and reasoning in information-dense scenarios.
  arXiv  Detail & Related papers  (2024-07-16T17:59:06Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)

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.