TrueBrief: Faithful Summarization through Small Language Models
Not on the map. Why?
Abstract (arXiv)
Large language models (LLMs) have exhibited remarkable proficiency in generating high-quality text; however, their propensity for producing hallucinations poses a significant challenge for their deployment in security-critical domains. In this work, we present TrueBrief, an end-to-end framework specifically designed to enhance the faithfulness of small LLMs (SLMs) primarily for the task of text summarization through a preference-optimization paradigm. Central to our framework is a data generation module that facilitates controlled hallucination injection to generate synthetic preference data. Our work provides insights into the impact of data quality and model size on preference-based optimization, highlighting the conditions under which these methods are most effective.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 12 Dec 2025.
Builds on
30 of 55 references.
References · 30
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2020Longformer: The Long-Document Transformercited by 3,413
- 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
- 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
- 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
- 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
- 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
- 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
18 more
- 2022Prompting GPT-3 To Be Reliablecited by 260
- 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 259
- 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 251
- 2023Fine-tuning Language Models for Factualitycited by 221
- 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 206
- 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
- 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 142
- 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
- 2024β-DPO: Direct Preference Optimization with Dynamic βcited by 90
- 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 87
- 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
- 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 72
- 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
- 2023Do Androids Know They're Only Dreaming of Electric Sheep?cited by 67
- 2023Teaching Language Models to Hallucinate Less with Synthetic Taskscited by 31
- 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
- 2023Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Productioncited by 21
- 2024Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detectorcited by 20
Built on by
Not cited yet.