ACL Findings2026
From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations
Pulkit Bansal, Raghvendra Kumar, Shakti Singh, Adam Jatowt, Sriparna Saha
Abstract
In an era of rampant misinformation, generating reliable news explanations is vital, especially for under-represented languages like Hindi. Lacking robust automated tools, Hindi faces challenges in scaling misinformation detection. To bridge this gap, we propose a novel framework integrating Direct Preference Optimization (DPO) with curriculum learning to align machine-generated explanations with human reasoning. Fact-checked explanations from credible sources serve as preferred responses, while LLM outputs highlight system limitations and serve as non-preferred responses. To refine task-specific alignment, we introduce two key parameters -- Actuality and Finesse -- into the DPO loss function, enhancing explanation quality and consistency. Experiments with LLMs (Mistral, Llama, Gemma) and PLMs (mBART, mT5) confirm the framework's effectiveness in generating coherent, contextually relevant explanations. This scalable approach combats misinformation and extends automated explanation generation to low-resource languages.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on16
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Uncertainty Estimation in Autoregressive Structured PredictionAndrey Malinin, Mark J. F. GalesICLR 2021 · 439 citations
- SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language ModelsPotsawee Manakul, Adian Liusie, Mark J. F. GalesEMNLP 2023 · 331 citations
- Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human SolutionsJiawei Zhou, Yixuan Zhang, Qianni Luo, Andrea G. Parker et al.CHI 2023 · 283 citations
Related papers
- Enhancing Alignment using Curriculum Learning & Ranked PreferencesPulkit Pattnaik, Rishabh Maheshwary, Kelechi Ogueji, Vikas Yadav et al.EMNLP Findings 2024 · 7 citations
- Fine-Tuning Language Models for FactualityKatherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning et al.ICLR 2024 · 270 citations
- Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and EnglishAvinash Anand, Kritarth Prasad, Chhavi Kirtani, Ashwin R. Nair et al.AAAI 2025 · 7 citations
- RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMsJohn Dang, Arash Ahmadian, Kelly Marchisio, Julia Kreutzer et al.EMNLP 2024 · 4 citations
- TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT AlignmentShicheng Li, Lei Li, Kun Ouyang, Shuhuai Ren et al.AAAI 2026 · 2 citations
