# Cognitive Biases in Large Language Models for News Recommendation

arXiv: https://arxiv.org/abs/2410.02897 · HTML: https://mlsanity.com/paper/2410.02897/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation](https://mlsanity.com/paper/2305.07609/) (2023)
- [Capturing Failures of Large Language Models via Human Cognitive Biases](https://mlsanity.com/paper/2202.12299/) (2022)
- [ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models](https://mlsanity.com/paper/2305.06566/) (2023)
- [Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias](https://mlsanity.com/paper/2308.00225/) (2023)
- [Addressing cognitive bias in medical language models](https://mlsanity.com/paper/2402.08113/) (2024)
- [Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency](https://mlsanity.com/paper/2401.10545/) (2024)
- [Prompt Learning for News Recommendation](https://mlsanity.com/paper/2304.05263/) (2023)
- [Item-side Fairness of Large Language Model-based Recommendation System](https://mlsanity.com/paper/2402.15215/) (2024)
- [A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News](https://mlsanity.com/paper/2306.10702/) (2023)
- [Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review](https://mlsanity.com/paper/2402.18590/) (2024)
- [KnowTuning: Knowledge-aware Fine-tuning for Large Language Models](https://mlsanity.com/paper/2402.11176/) (2024)
- [Feature-Level Debiased Natural Language Understanding](https://mlsanity.com/paper/2212.05421/) (2022)
- [Towards Empathetic Conversational Recommender Systems](https://mlsanity.com/paper/2409.10527/) (2024)
- [Public discourse and social network echo chambers driven by socio-cognitive biases](https://mlsanity.com/paper/2002.03915/) (2020)

## Built on by (most cited first, 8 of 8)

- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [DeepShop: A Benchmark for Deep Research Shopping Agents](https://mlsanity.com/paper/2506.02839/) (2025)
- [MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization](https://mlsanity.com/paper/2410.07672/) (2024)
- [Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations](https://mlsanity.com/paper/2502.01349/) (2025)
- [EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning](https://mlsanity.com/paper/2603.21728/) (2026)
- [Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making](https://mlsanity.com/paper/2504.04141/) (2025)
- [SearchJev: A Fast and Calibrated System-1 Model for Search Agents](https://mlsanity.com/paper/2610.05107/) (2026)
- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

Despite large language models (LLMs) increasingly becoming important components of news recommender systems, employing LLMs in such systems introduces new risks, such as the influence of cognitive biases in LLMs. Cognitive biases refer to systematic patterns of deviation from norms or rationality in the judgment process, which can result in inaccurate outputs from LLMs, thus threatening the reliability of news recommender systems. Specifically, LLM-based news recommender systems affected by cognitive biases could lead to the propagation of misinformation, reinforcement of stereotypes, and the formation of echo chambers. In this paper, we explore the potential impact of multiple cognitive biases on LLM-based news recommender systems, including anchoring bias, framing bias, status quo bias and group attribution bias. Furthermore, to facilitate future research at improving the reliability of LLM-based news recommender systems, we discuss strategies to mitigate these biases through data augmentation, prompt engineering and learning algorithms aspects.