# Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection

arXiv: https://arxiv.org/abs/2510.22395 · HTML: https://mlsanity.com/paper/2510.22395/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 25 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks](https://mlsanity.com/paper/1909.01716/) (2019)
- [SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes](https://mlsanity.com/paper/2504.11975/) (2025)
- [SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakes](https://mlsanity.com/paper/2403.07726/) (2024)
- [When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA](https://mlsanity.com/paper/2510.04849/) (2025)
- [HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification](https://mlsanity.com/paper/2504.07069/) (2025)
- [Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers](https://mlsanity.com/paper/2310.10627/) (2023)

## Built on by (most cited first, 2 of 2)

- [Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking](https://mlsanity.com/paper/2608.01021/) (2026)
- ["AGI" team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa](https://mlsanity.com/paper/2511.18301/) (2025)

## Abstract (arXiv)

We introduce the CAP (Confabulations from ACL Publications) dataset, a multilingual resource for studying hallucinations in large language models (LLMs) within scientific text generation. CAP focuses on the scientific domain, where hallucinations can distort factual knowledge, as they frequently do. In this domain, however, the presence of specialized terminology, statistical reasoning, and context-dependent interpretations further exacerbates these distortions, particularly given LLMs' lack of true comprehension, limited contextual understanding, and bias toward surface-level generalization. CAP operates in a cross-lingual setting covering five high-resource languages (English, French, Hindi, Italian, and Spanish) and four low-resource languages (Bengali, Gujarati, Malayalam, and Telugu). The dataset comprises 900 curated scientific questions and over 7000 LLM-generated answers from 16 publicly available models, provided as question-answer pairs along with token sequences and corresponding logits. Each instance is annotated with a binary label indicating the presence of a scientific hallucination, denoted as a factuality error, and a fluency label, capturing issues in the linguistic quality or naturalness of the text. CAP is publicly released to facilitate advanced research on hallucination detection, multilingual evaluation of LLMs, and the development of more reliable scientific NLP systems.