# Bridging Social Psychology and LLM Reasoning: Conflict-Aware Meta-Review Generation via Cognitive Alignment

arXiv: https://arxiv.org/abs/2503.13879 · HTML: https://mlsanity.com/paper/2503.13879/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [The Consciousness Prior](https://mlsanity.com/paper/1709.08568/) (2017)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews](https://mlsanity.com/paper/2408.10365/) (2024)
- [Planning Like Human: A Dual-process Framework for Dialogue Planning](https://mlsanity.com/paper/2406.05374/) (2024)
- [Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation](https://mlsanity.com/paper/2305.01498/) (2023)
- [Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review](https://mlsanity.com/paper/2410.03019/) (2024)
- [LLMs as Meta-Reviewers' Assistants: A Case Study](https://mlsanity.com/paper/2402.15589/) (2024)
- [Deep Reasoning Networks: Thinking Fast and Slow](https://mlsanity.com/paper/1906.00855/) (2019)
- [Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs](https://mlsanity.com/paper/1708.03310/) (2017)
- [A Neural-Symbolic Approach to Natural Language Understanding](https://mlsanity.com/paper/2203.10557/) (2022)
- [AcademicGPT: Empowering Academic Research](https://mlsanity.com/paper/2311.12315/) (2023)
- [Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models](https://mlsanity.com/paper/2410.21728/) (2024)
- [SEAGraph: Unveiling the Whole Story of Paper Review Comments](https://mlsanity.com/paper/2412.11939/) (2024)

## Built on by (most cited first, 2 of 2)

- [Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator](https://mlsanity.com/paper/2507.11810/) (2025)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)

## Abstract (arXiv)

The rapid growth of scholarly submissions has overwhelmed traditional peer review systems, driving the need for intelligent automation to preserve scientific rigor. While large language models (LLMs) show promise in automating manuscript critiques, their ability to synthesize high-stakes meta-reviews, which require conflict-aware reasoning and consensus derivation, remains underdeveloped. Existing methods fail to effectively handle conflicting viewpoints within differing opinions, and often introduce additional cognitive biases, such as anchoring effects and conformity bias.To overcome these limitations, we propose the Cognitive Alignment Framework (CAF), a dual-process architecture that transforms LLMs into adaptive scientific arbitrators. By operationalizing Kahneman's dual-process theory, CAF introduces a three-step cognitive pipeline: review initialization, incremental integration, and cognitive alignment.Empirical validation shows that CAF outperforms existing LLM-based methods, with sentiment consistency gains reaching up to 19.47% and content consistency improving by as much as 12.95%.