# Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models

arXiv: https://arxiv.org/abs/2406.02143 · HTML: https://mlsanity.com/paper/2406.02143/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 74 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://mlsanity.com/paper/2305.12744/) (2023)
- [GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media](https://mlsanity.com/paper/2004.11648/) (2020)
- [Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations](https://mlsanity.com/paper/2010.03640/) (2020)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Stance Detection on Social Media: State of the Art and Trends](https://mlsanity.com/paper/2006.03644/) (2020)
- [Stance Detection with Bidirectional Conditional Encoding](https://mlsanity.com/paper/1606.05464/) (2016)
- [SemEval-2017 Task 8: RumourEval: Determining rumour veracity and support for rumours](https://mlsanity.com/paper/1704.05972/) (2017)
- [RumourEval 2019: Determining Rumour Veracity and Support for Rumours](https://mlsanity.com/paper/1809.06683/) (2018)
- [Analysing How People Orient to and Spread Rumours in Social Media by Looking at Conversational Threads](https://mlsanity.com/paper/1511.07487/) (2015)
- [Towards Few-Shot Fact-Checking via Perplexity](https://mlsanity.com/paper/2103.09535/) (2021)
- [Can we trust the evaluation on ChatGPT?](https://mlsanity.com/paper/2303.12767/) (2023)
- [All-in-one: Multi-task Learning for Rumour Verification](https://mlsanity.com/paper/1806.03713/) (2018)
- [Interpretable Rumor Detection in Microblogs by Attending to User Interactions](https://mlsanity.com/paper/2001.10667/) (2020)
- [Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning](https://mlsanity.com/paper/2204.08143/) (2022)
- [Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning](https://mlsanity.com/paper/2212.01117/) (2022)
- [Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks](https://mlsanity.com/paper/2110.04522/) (2021)
- [Causal Understanding of Fake News Dissemination on Social Media](https://mlsanity.com/paper/2010.10580/) (2020)
- [Turing at SemEval-2017 Task 8: Sequential Approach to Rumour Stance Classification with Branch-LSTM](https://mlsanity.com/paper/1704.07221/) (2017)
- [Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity](https://mlsanity.com/paper/1909.08211/) (2019)
- [Reinforcement Retrieval Leveraging Fine-grained Feedback for Fact Checking News Claims with Black-Box LLM](https://mlsanity.com/paper/2404.17283/) (2024)
- [Discourse-Aware Rumour Stance Classification in Social Media Using Sequential Classifiers](https://mlsanity.com/paper/1712.02223/) (2017)

## Built on by (most cited first, 5 of 5)

- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)
- [Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation](https://mlsanity.com/paper/2506.07211/) (2025)
- [Crowd Intelligence for Early Misinformation Prediction on Social Media](https://mlsanity.com/paper/2408.04463/) (2024)
- [LLM-based Few-Shot Early Rumor Detection with Imitation Agent](https://mlsanity.com/paper/2512.18352/) (2025)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

Learning multi-task models for jointly detecting stance and verifying rumors poses challenges due to the need for training data of stance at post level and rumor veracity at claim level, which are difficult to obtain. To address this issue, we leverage large language models (LLMs) as the foundation annotators for the joint stance detection (SD) and rumor verification (RV) tasks, dubbed as JSDRV. We introduce a novel reinforcement tuning framework to enhance the joint predictive capabilities of LLM-based SD and RV components. Specifically, we devise a policy for selecting LLM-annotated data at the two levels, employing a hybrid reward mechanism to choose high-quality labels for effective LLM fine-tuning on both tasks. Results demonstrate that JSDRV improves the capabilities of LLMs in the joint tasks, not only outperforming state-of-the-art methods but also generalizing to non-LLMs accommodated as task models.