CITETRACE dataset and evaluation framework show 30.6% of citations distort sources and 27.1% use domain-inappropriate sources in search-augmented LLMs, with provider differences explaining 88-96% of quality variance.
arXiv preprint arXiv:2506.05334 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Audit of ChatGPT, Copilot, Gemini and Perplexity finds ~16% of cited sources are AI-generated across 712 queries on politics, health and environment.
ECC calibrates semantic embeddings with model comparisons via Bradley-Terry profiles and mixture weights to cluster queries by latent LLM capabilities, claiming 17-18 point gains in ranking quality over baselines.
MARCA is a bilingual benchmark using 52 questions and validated checklists to evaluate LLM web-search completeness and correctness in English and Portuguese.
Position paper mapping causal inference opportunities across the LLM development pipeline from pretraining to evaluation to address confounding and non-stationarity.
citing papers explorer
-
Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs
CITETRACE dataset and evaluation framework show 30.6% of citations distort sources and 27.1% use domain-inappropriate sources in search-augmented LLMs, with provider differences explaining 88-96% of quality variance.
-
Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources
Audit of ChatGPT, Copilot, Gemini and Perplexity finds ~16% of cited sources are AI-generated across 712 queries on politics, health and environment.
-
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
ECC calibrates semantic embeddings with model comparisons via Bradley-Terry profiles and mixture weights to cluster queries by latent LLM capabilities, claiming 17-18 point gains in ranking quality over baselines.
-
MARCA: A Checklist-Based Benchmark for Multilingual Web Search
MARCA is a bilingual benchmark using 52 questions and validated checklists to evaluate LLM web-search completeness and correctness in English and Portuguese.
-
Causal methods for LLM development and evaluation
Position paper mapping causal inference opportunities across the LLM development pipeline from pretraining to evaluation to address confounding and non-stationarity.