A unified toolkit and interactive web UI for detecting contextual hallucinations in retrieval-augmented, agentic, and memory-grounded LLM systems, and as a faithfulness gate within long-term memory systems is demonstrated.
Abstract
SIRIN (Semantic Inconsistency Recognition and Inspection Nexus) is a unified toolkit and interactive web UI for detecting contextual hallucinations (fluent, plausible responses unsupported by the provided evidence) in retrieval-augmented, agentic, and memory-grounded LLM systems. SIRIN unifies three detector paradigms (representation probing, uncertainty estimation, and judge-style verification) and the complementary task of pre-generation query answerability under one interface, configuration system, and evaluation pipeline, supporting response- and span-level inspection in both white-box and black-box settings. The web UI enables live analysis of user-supplied context-query-answer triples through hallucination scores, unsupported-span highlighting, and side-by-side detector comparison, with a lightweight plug-in design for adding new detectors. We demonstrate SIRIN on hallucination detection, query answerability, and as a faithfulness gate within long-term memory systems. The source code is publicly available at https://github.com/sb-ai-lab/SIRIN.
HallDetect, a lightweight, reference-free, and black-box framework for hallucination detection, is presented, a lightweight, reference-free, and black-box framework for hallucination detection that is evaluated not only on summarization but across a broader range of source-grounded generation settings.
Achir Oukelmoun, N. Semmar, Gäel de Chalendar· 0 citations
Faithfulness hallucinations, where large language models generate outputs unsupported by retrieved evidence, remain a central challenge for trustworthy AI. We present a systematic empirical evaluation of faithfulness in retrieval-augmented generation (RAG) systems using two benchmark datasets, HotpotQA and HaluBench, covering both multi-hop reasoning and single-hop hallucination detection. We analyze three small-to-mid-sized (2B-8B) open-weight LLMs in combination with multiple retrieval strategies, including sparse, dense, and hybrid approaches, as well as score-based and rank-based fusion techniques, enabling a comprehensive assessment of retrieval-generation interactions. By disentangling retrieval and generation errors, we characterize how different pipeline components contribute to hallucinations in RAG systems. Our analysis provides actionable insights and practical evaluation protocols, highlighting the critical role of robust retrieval and careful system design. These findings offer a benchmarking-oriented perspective for developing more reliable and faithful RAG systems within evaluated model scales.
C. Mala, Gizem Gezici, Fosca Giannotti· Machine-mediated learning· 0 citations
The issue of hallucination detection for Retrieval-Augmented Generation (RAG) systems is an ongoing reliability challenge that arises with the scale up of LLM deployment. We introduce the HaloGuard: a systems-integration study that integrates three types of signals, multi-judge LLM consensus, uncertainty quantification through temperature sampling, and lexical text features, and evaluate with LibreEval (10,871 samples; GPT-4o, Claude-3.5-Sonnet, Llama-3.1-8B). They all rely on previous work; the novel aspect of the present paper is their principled combination, empirical decomposition through ablation, calibration analysis, and deployment characterization over operating thresholds, hallucination types, and six languages At a conservative threshold, HaloGuard achieves AUC-ROC = 0.986 [95% CI: 0.981-0.991] and F1 = 0.665 [0.639-0.690]; at the balanced max-F1 threshold, F1 = 0.769 (Precision = 0.812 / Recall = 0.731), directly addressing the precision-1.000 operating-point artifact. A fine-tuned variant (HaloGuard-FT, DeBERTa-v3-base) reaches F1 = 0.847 [0.831-0.863] and AUC = 0.994 [0.991-0.997]. Weight sensitivity analysis confirms F1 is stable across judge weight alpha in [0.5, 0.7] (F1 range <= 0.016), ruling out weight cherry-picking. Additional analyses quantify a 2.15x novelty differential (p < 0.001), source-attribution correlation (r = -0.319), and systematic cross-lingual F1 degradation (EN: 0.665 -> JA: 0.543). Calibration is well-behaved (ECE = 0.043). All results are scoped to LibreEval; cross-dataset validation on RAGTruth is the stated priority next step. Full judge prompts, hyperparameters, and code are documented for reproducibility.
Harshath R, G. S, S. Thangavel et al.· 2026 International Conferenc...· 0 citations
With the rise in the usage of Retrieval-Augmented Generation (RAG) systems to improve the factual accuracy of the large language models (LLM), there still exists a concern regarding these systems producing hallucinating outputs not grounded in the retrieved documents. Although prior work has studied general hallucination detection, the specific challenge of numerical fabrication remains unquantified. This research study analyzes 500 RAG outputs using GPT-3.5-turbo on MS MARCO queries to address this specific challenge and found that 38.2% of failures involve numerical fabrication. The evaluation consists of four detection methods that span different paradigms: embedding-based (Semantic Similarity), metric-based (BERTScore), LLM-based (GPT-4o-mini), and a number-aware heuristic. The results show that all standard methods struggle with numerical hallucinations, notably GPT-4o-mini achieves only 25.7% recall on numerical failures despite being a state-of-the-art LLM judge. In contrast, the simple number-aware heuristic of this research study achieves a 100% recall on numerical failures with F1=0.616, significantly outperforming all baselines (McNemar's test, p<0.001). These findings highlight numerical fabrication as a critical gap in current hallucination detection approaches and recommend the need for specialized, number-aware methods in RAG systems.
S. Singha Roy· Annual International ACM SIG...· 0 citations
Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why. To close this gap, we introduce Grounding-Aware Sensitivity by Perturbation (GASP), a span-level detector that scores each answer sentence by how strongly its likelihood depends on the retrieved evidence, a quantity we term grounding sensitivity. GASP holds the answer fixed and re-scores it under the full context, under no context, and with each chunk removed, then measures the log-likelihood drops and Jensen-Shannon divergences (JSD). The likelihood of a grounded sentence collapses once its supporting passage is removed, whereas a hallucinated sentence is almost unaffected, a contrast we interpret by casting decoding as a random nonlinear iterated function system (RNIFS). We evaluate GASP on three benchmarks (RAGTruth, TofuEval, RAGBench) with three instruction-tuned scorers from two model families (Qwen2.5-0.5B, Qwen2.5-1.5B, and SmolLM2-1.7B) under a leakage-clean protocol. On RAGTruth it reaches a response-level area under the ROC curve (AUC) of about 0.73 and a span-level AUC of about 0.67, improving significantly over perplexity and by clear margins over length, whole-context natural language inference (NLI), and self-consistency baselines. The only baseline competitive at the span level is a well-configured chunk-level entailment verifier, which requires a separate model, whereas a training-free threshold on the grounding features matches the trained classifier without labeled data and serves as the default detector. Beyond RAGTruth, the signal transfers to TofuEval but not to short-answer question answering in RAGBench, showing GASP is best suited to outputs constructed from the retrieved context rather than answers recoverable from parametric knowledge.
A concise two-axis framework that integrates an “intrinsic-extrinsic” distinction in source attribution introduced by Ji et al. with a “faithfulness-factuality” distinction in contextual grounding surveyed is presented, yielding four clearly defined hallucination types applicable across tasks, modalities and architectures.
Misbah Khan, Preston Billion-Polak, T. Khoshgoftaar· IEEE Access· 0 citations