mlsanityData to 7 Oct 2026

MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection

arXiv 2403.00964 ↗First posted 1 Mar 2024cs.CL cs.LGcited by 4

On the map: Synthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data

Abstract (arXiv)

In Natural Language Generation (NLG), contemporary Large Language Models (LLMs) face several challenges, such as generating fluent yet inaccurate outputs and reliance on fluency-centric metrics. This often leads to neural networks exhibiting "hallucinations". The SHROOM challenge focuses on automatically identifying these hallucinations in the generated text. To tackle these issues, we introduce two key components, a data augmentation pipeline incorporating LLM-assisted pseudo-labelling and sentence rephrasing, and a voting ensemble from three models pre-trained on Natural Language Inference (NLI) tasks and fine-tuned on diverse datasets.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Self-improving MLLMs and synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 7 of its 23 references that are in the map. First posted on arXiv 1 Mar 2024.

Builds on

7 of 23 references.

References · 7

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  4. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  5. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
  6. 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
  7. 2016Definition Modeling: Learning to define word embeddings in natural languagecited by 46

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024SemEval-2024 Shared Task 6: SHROOM, a Shared-task on Hallucinations and Related Observable Overgeneration Mistakescited by 24
  2. 2025HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detectioncited by 1
  3. 2026Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insightscited by 0
  4. 2026Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summariescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
  3. 2025Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
  4. 2024Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responses
  5. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answering
  6. 2026Scalable Token-Level Hallucination Detection in Large Language Models
  7. 2024The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States
  8. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models