Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

• URL: http://arxiv.org/abs/2509.17671v1
• Date: Mon, 22 Sep 2025 12:14:11 GMT
• Title: Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications
• Authors: Selva Taş, Mahmut El Huseyni, Özay Ezerceli, Reyhan Bayraktar, Fatma Betül Terzioğlu,
• Abstract summary: This paper introduces Turk-LettuceDetect, the first suite of hallucination detection models specifically designed for Turkish RAG applications.<n>These models were trained on a machine-translated version of the RAGTruth benchmark dataset containing 17,790 instances across question answering, data-to-text generation, and summarization tasks.<n>Our experimental results show that the ModernBERT-based model achieves an F1-score of 0.7266 on the complete test set, with particularly strong performance on structured tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The widespread adoption of Large Language Models (LLMs) has been hindered by their tendency to hallucinate, generating plausible but factually incorrect information. While Retrieval-Augmented Generation (RAG) systems attempt to address this issue by grounding responses in external knowledge, hallucination remains a persistent challenge, particularly for morphologically complex, low-resource languages like Turkish. This paper introduces Turk-LettuceDetect, the first suite of hallucination detection models specifically designed for Turkish RAG applications. Building on the LettuceDetect framework, we formulate hallucination detection as a token-level classification task and fine-tune three distinct encoder architectures: a Turkish-specific ModernBERT, TurkEmbed4STS, and multilingual EuroBERT. These models were trained on a machine-translated version of the RAGTruth benchmark dataset containing 17,790 instances across question answering, data-to-text generation, and summarization tasks. Our experimental results show that the ModernBERT-based model achieves an F1-score of 0.7266 on the complete test set, with particularly strong performance on structured tasks. The models maintain computational efficiency while supporting long contexts up to 8,192 tokens, making them suitable for real-time deployment. Comparative analysis reveals that while state-of-the-art LLMs demonstrate high recall, they suffer from low precision due to over-generation of hallucinated content, underscoring the necessity of specialized detection mechanisms. By releasing our models and translated dataset, this work addresses a critical gap in multilingual NLP and establishes a foundation for developing more reliable and trustworthy AI applications for Turkish and other languages.

Related papers

• BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish [0.0]
  We introduce BIRDTurk, the first Turkish adaptation of the BIRD benchmark.<n>BirderTurk is constructed through a controlled translation pipeline that adapts schema identifiers to Turkish.<n>We evaluate inference-based prompting, agentic multi-stage reasoning, and supervised fine-tuning.
  arXiv  Detail & Related papers  (2026-02-03T15:21:00Z)
• TurkEmbed: Turkish Embedding Model on NLI & STS Tasks [0.0]
  TurkEmbed is a novel Turkish language embedding model designed to outperform existing models.<n>It utilizes a combination of diverse datasets and advanced training techniques, including matryoshka representation learning.<n>It surpasses the current state-of-the-art model, Emrecan, on All-NLI-TR and STS-b-TR benchmarks, achieving a 1-4% improvement.
  arXiv  Detail & Related papers  (2025-11-11T15:54:52Z)
• HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy [48.68088917291552]
  We introduce a comprehensive hallucination taxonomy with 11 categories across various NLG tasks.<n>We propose the HAllucination Detection (HAD) models, which integrate hallucination detection, span-level identification, and correction into a single inference process.
  arXiv  Detail & Related papers  (2025-10-22T07:28:37Z)
• Ask a Local: Detecting Hallucinations With Specialized Model Divergence [0.16874375111244325]
  We introduce "Ask a Local", a novel hallucination detection method for large language models.<n>Our approach computes divergence between perplexity distributions of language-specialized models to identify potentially hallucinated spans.<n>Our results on a human-annotated question-answer dataset spanning 14 languages demonstrate consistent performance across languages.
  arXiv  Detail & Related papers  (2025-06-03T20:00:49Z)
• Towards Typologically Aware Rescoring to Mitigate Unfaithfulness in Lower-Resource Languages [9.426642998924724]
  Multilingual large language models generate non-faithful output in resource-constrained languages.<n>To mitigate unfaithfulness in such settings, we propose using computationally light auxiliary models to rescore the outputs of larger architectures.<n>We show that monolingual 4-layer BERT models pretrained from scratch on less than 700 MB of data without fine-tuning are able to identify faithful summaries with a mean accuracy of 88.33%.
  arXiv  Detail & Related papers  (2025-02-24T21:22:19Z)
• Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks [0.0]
  We provide a Transformer-based model and a baseline benchmark for the Turkish Language. We successfully fine-tuned a Turkish BERT model, namely BERTurk, to many downstream tasks and evaluated with a the Turkish Benchmark dataset.
  arXiv  Detail & Related papers  (2024-01-30T19:27:04Z)
• Fine-tuning Language Models for Factuality [96.5203774943198]
  Large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations' In this work, we fine-tune language models to be more factual, without human labeling.
  arXiv  Detail & Related papers  (2023-11-14T18:59:15Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)
• Improving Massively Multilingual ASR With Auxiliary CTC Objectives [40.10307386370194]
  We introduce our work on improving performance on FLEURS, a 102-language open ASR benchmark. We investigate techniques inspired from recent Connectionist Temporal Classification ( CTC) studies to help the model handle the large number of languages. Our state-of-the-art systems using self-supervised models with the Conformer architecture improve over the results of prior work on FLEURS by a relative 28.4% CER.
  arXiv  Detail & Related papers  (2023-02-24T18:59:51Z)
• mFACE: Multilingual Summarization with Factual Consistency Evaluation [79.60172087719356]
  Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries. We leverage factual consistency evaluation models to improve multilingual summarization.
  arXiv  Detail & Related papers  (2022-12-20T19:52:41Z)
• Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval [51.60862829942932]
  We present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. For sentence-level CLIR, we demonstrate that state-of-the-art performance can be achieved. However, the peak performance is not met using the general-purpose multilingual text encoders off-the-shelf', but rather relying on their variants that have been further specialized for sentence understanding tasks.
  arXiv  Detail & Related papers  (2021-01-21T00:15:38Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

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.