Skip to content
Review

Fluent but Fallible: Benchmarking Hallucination and Factual Reliability in Large Language Models

Oct 2026 · 0 citations · 62 references
Computer Science

TL;DR

A thorough comparative analysis using a variety of metrics of ten advanced LLMs shows a fundamental trade-off between response completeness and factual reliability, intensified by prompt complexity.

Abstract

Large Language Models (LLMs) have significantly advanced natural language processing and artificial intelligence applications through their capabilities in reasoning, text generation and knowledge retrieval. However, LLMs are still vulnerable to two important challenges: hallucination, generating factually incorrect or fabricated content, and response deviation, meaning systematic deviations from ground-truth responses. These limitations raise serious concerns regarding reliability and trustworthiness in academic and research environments. This study offers a thorough comparative analysis using a variety of metrics of ten advanced LLMs ChatGPT, Gemini, Claude~3.5~Sonnet, LLaMA~3, Mistral, Grok, Perplexity, DeepSeek~V3, Falcon, and Gemma based on a benchmark consisting of 70 carefully designed academic prompts across four complexity levels: Basic, Explanation, Advanced, and Tricky, evaluated in February 2025 on specific model versions. Each response was independently evaluated by three reviewers using five metrics: Accuracy, Precision, Recall, Response Deviation Index, and Hallucination Index. Perplexity and DeepSeek~V3 achieved the highest overall accuracy, while Gemini demonstrated strong recall and a well-balanced performance profile across all five metrics. LLaMA~3 showed strong resistance against hallucinations through a conservative method of generation. Advanced-level prompts proved most challenging across all models, while Tricky prompts were handled more reliably owing to their binary true/false structure. Falcon achieved perfect precision and zero hallucinations, but at the cost of the lowest recall and the highest response deviation. The results show a fundamental trade-off between response completeness and factual reliability, intensified by prompt complexity.

View source

Similar papers

#artificial intelligence Preprint Nov 2026

When Ground Truth Is Not Ground Truth: Automatic Labeling for Hallucination Detection

Hallucinations in Large Language Models (LLMs) remain a major challenge, as they can produce misleading, factually incorrect, or unverifiable information, thereby undermining their trustworthiness and reliability. However, reliable ground-truth labels remain a key challenge in evaluating hallucination detectors. Recent...

Rounak Sen, Divya Kumari, Deeksha Varshney · 0 citations
Open access Sep 2026

Evaluating the Efficiency of Large Language Models in Detecting and Mitigating Hallucinations Using a Curated Domain-Oriented Dataset and Post-Hoc Retrieval

Results show that relevant external evidence can improve the reliability and consistency of LLM based hallucination detection and the proposed approach uses retrieval to verify claims and reclassify responses when the initial judgment needs evidence.

Chandra Sekhar Sanaboina, T. Surekha · 0 citations
Conference Oct 2026

Structured Hallucinations in Small Language Models: Repeatability, Attention Signatures, and Context Contagion

In this paper, we present an empirical analysis of hallucination behavior in small language models (1.5B–7B parameters), addressing the question of whether such failures are stochastic or structured. Our analysis of 4,500 responses from three instruction-tuned models, evaluated on TruthfulQA and HaluEval, reveals that...

Kushagra Agrawal, Yu-Ming Feng, Hang-Jun Che et al. · 0 citations
Preprint Nov 2026

From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations?

HaluCheck, a large-scale, bilingual benchmark comprising over 42k instances spanning both factual hallucinations in text and faithfulness hallucinations in agent trajectories, provides a solid basis for benchmarking and diagnosing LLM reliability across text and agent scenarios.

Han-Yu Qiu, Ze-Li Liu, Zhe Zhao et al. · 0 citations
Conference Sep 2026

Hallucination Detection and Reduction in Genai (LLMs)

Hallucinations are false or unverifiable outputs generated by Large Language Models (LLMs) that reduce their trustworthiness in critical applications such as healthcare, education, and research. This paper proposes a hybrid framework that unifies three complementary verification signals for the detection and reduction...

Radhika K. R., Sumit Gupta, Nagesh H. Shenoy et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.