From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913175224451072 |
|---|---|
| author | Bansal, Pulkit Kumar, Raghvendra Singh, Shakti Jatowt, Adam Saha, Sriparna |
| author_facet | Bansal, Pulkit Kumar, Raghvendra Singh, Shakti Jatowt, Adam Saha, Sriparna |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05179 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations Bansal, Pulkit Kumar, Raghvendra Singh, Shakti Jatowt, Adam Saha, Sriparna Computation and Language 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. |
| title | From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.05179 |