# TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection

arXiv: https://arxiv.org/abs/2402.07776 · HTML: https://mlsanity.com/paper/2402.07776/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 66 references that are in the map.
- First posted on arXiv 12 Feb 2024.

## Builds on (most cited first, 30 of 39)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Fighting an Infodemic: COVID-19 Fake News Dataset](https://mlsanity.com/paper/2011.03327/) (2020)
- [Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection](https://mlsanity.com/paper/2309.12247/) (2023)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [All-in-one: Multi-task Learning for Rumour Verification](https://mlsanity.com/paper/1806.03713/) (2018)
- [Prototypical Verbalizer for Prompt-based Few-shot Tuning](https://mlsanity.com/paper/2203.09770/) (2022)
- [Generating Fact Checking Briefs](https://mlsanity.com/paper/2011.05448/) (2020)
- [Embracing Domain Differences in Fake News: Cross-domain Fake News Detection using Multi-modal Data](https://mlsanity.com/paper/2102.06314/) (2021)
- [Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Clues](https://mlsanity.com/paper/2108.10509/) (2021)
- [Managing extreme AI risks amid rapid progress](https://mlsanity.com/paper/2310.17688/) (2023)
- [Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4](https://mlsanity.com/paper/2305.14928/) (2023)

## Built on by (most cited first, 10 of 10)

- [Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection](https://mlsanity.com/paper/2406.11260/) (2024)
- [Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework](https://mlsanity.com/paper/2508.03092/) (2025)
- [HAWK: A Hierarchical Workflow Framework for Multi-Agent Collaboration](https://mlsanity.com/paper/2507.04067/) (2025)
- [AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions](https://mlsanity.com/paper/2509.11151/) (2025)
- [The Alignment Bottleneck in Decomposition-Based Claim Verification](https://mlsanity.com/paper/2602.10380/) (2026)
- [TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning](https://mlsanity.com/paper/2604.12184/) (2026)
- [An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection](https://mlsanity.com/paper/2605.02259/) (2026)
- [ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation](https://mlsanity.com/paper/2606.27736/) (2026)
- [GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning](https://mlsanity.com/paper/2607.20730/) (2026)
- [MRAFnd: Multimodal Retrieval-Augmented Framework for Zero-Shot Fake News Detection](https://mlsanity.com/paper/2608.01430/) (2026)

## Abstract (arXiv)

The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have made progress in detecting fake news accurately, their reliability may be compromised caused by the non-transparent reasoning processes, poor generalization abilities and inherent risks of integration with large language models (LLMs). To address this challenge, we propose methodname, a novel framework for trustworthy fake news detection that prioritizes explainability, generalizability and controllability of models. This is achieved via a dual-system framework that integrates cognition and decision systems, adhering to the principles above. The cognition system harnesses human expertise to generate logical predicates, which guide LLMs in generating human-readable logic atoms. Meanwhile, the decision system deduces generalizable logic rules to aggregate these atoms, enabling the identification of the truthfulness of the input news across diverse domains and enhancing transparency in the decision-making process. Finally, we present comprehensive evaluation results on four datasets, demonstrating the feasibility and trustworthiness of our proposed framework. Our implementation is available at urlhttps://github.com/less-and-less-bugs/TrustTELLER.