Skip to content
← Back to explorer

Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information

Joshua Harris, Fan Grayson, Felix Feldman, Timothy Laurence, Toby Nonnenmacher, Oliver Higgins, Leo Loman, Selina Patel, Thomas Finnie, Samuel Collins, Michael Borowitz · May 9, 2025 · Citations: 0

Automatic Metrics Medicine Web Browsing
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 4, 2026, 4:21 PM

Recent

Extraction refreshed

Mar 8, 2026, 5:27 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.55

Abstract

As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use. This is particularly critical in the domains of medicine and public health, where failure to retrieve relevant, accurate, and current information could significantly impact UK residents. However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health. To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries. To create PubHealthBench we extract free text from 687 current UK government guidance documents and implement an automated pipeline for generating MCQA samples. Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use. However, in the free form setup we see lower performance with no model scoring >75%. Therefore, while there are promising signs that state of the art (SOTA) LLMs are an increasingly accurate source of public health information, additional safeguards or tools may still be needed when providing free form responses.

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Eval-Fit Score

25/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Moderate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use.

Evaluation Modes

strong

Automatic Metrics

Confidence: Moderate Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use.

Benchmarks / Datasets

strong

Pubhealthbench

Confidence: Moderate Source: Persisted extraction evidenced

Useful for quick benchmark comparison.

Evidence snippet: To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries.

Reported Metrics

strong

Accuracy

Confidence: Moderate Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: As Large Language Models (LLMs) become widely accessible, a detailed understanding of their knowledge within specific domains becomes necessary for successful real world use.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Freeform
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Web Browsing
  • Quality controls: Not reported
  • Confidence: 0.55
  • Flags: ambiguous, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

Pubhealthbench

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health. HFEPX signals include Automatic Metrics, Web Browsing with confidence 0.55. Updated from current HFEPX corpus.

Generated Mar 8, 2026, 5:27 PM · Grounded in abstract + metadata only

Key Takeaways

  • However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health.
  • To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Cross-check benchmark overlap: Pubhealthbench.
  • Validate metric comparability (accuracy).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health.
  • To address this issue, this paper introduces a new benchmark, PubHealthBench, with over 8000 questions for evaluating LLMs' Multiple Choice Question Answering (MCQA) and free form responses to public health queries.
  • Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use.

Why It Matters For Eval

  • However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health.
  • Assessing 24 LLMs on PubHealthBench we find the latest proprietary LLMs (GPT-4.5, GPT-4.1 and o1) have a high degree of knowledge, achieving >90% accuracy in the MCQA setup, and outperform humans with cursory search engine use.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Pubhealthbench

  • Pass: Metric reporting is present

    Detected: accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote