Papers with deliberate reasoning
NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models have shown impressive performance on various benchmarks, yet their ability to engage in deliberate reasoning remains questionable. |
| Approach: | They propose to penalize quick, intuitive "System 1" thinking by combining linguistic isolation with resistance to intuitive shortcuts to assess model's reasoning abilities. |
| Outcome: | The proposed model penalizes quick, intuitive “System 1” thinking, isolating fundamental reasoning skills. |
Language Models Don’t Learn the Physical Manifestation of Language (2024.acl-long)
Copied to clipboard
| Challenge: | a new study examines the differences between language-only models and humans . we show that language-based models do not learn the physical manifestation of language . |
| Approach: | They propose to use a series of tasks to investigate visual-auditory properties of language to test their hypothesis. |
| Outcome: | The proposed model does not learn the physical manifestation of language . the results highlight the limitations of linguistic knowledge acquired without sensory experience . |
Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting. |
| Approach: | They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty. |
| Outcome: | The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST. |
Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents (2024.findings-emnlp)
Copied to clipboard
Zengqing Wu, Run Peng, Shuyuan Zheng, Qianying Liu, Xu Han, Brian Kwon, Makoto Onizuka, Shaojie Tang, Chuan Xiao
| Challenge: | Large Language Models (LLMs) are increasingly used in social simulations, where they are guided by carefully crafted instructions to exhibit human-like behaviors. |
| Approach: | They propose to use Large Language Models (LLMs) as agents to simulate the gradual transition from non-cooperative to cooperative behaviors of agents. |
| Outcome: | The proposed model can simulate the gradual transition from non-cooperative to cooperative behaviors in three competitive scenarios. |
Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Writing arguments requires integrating high-level beliefs from various perspectives . current language models generate outputs autoregressively, resulting in limited diversity and coherence . |
| Approach: | They propose a persona-based multi-agent framework for argument writing that integrates beliefs from different perspectives into a coherent narrative. |
| Outcome: | The proposed framework generates more diverse arguments by both automatic and human evaluations. |
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on the issue of hallucination in large language models. |
| Approach: | They propose a framework that allows an explicit slow thinking generation process for mitigating hallucinations during inference. |
| Outcome: | The proposed framework outperforms baseline approaches on English and Chinese datasets. |
Large Language Models Can Learn Temporal Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Temporal reasoning (TR) is a fundamental ability of large language models (LLMs) however, there is neo-standard methods to perform TR, which are not suitable for large language model applications. |
| Approach: | They propose a framework to enhance temporal reasoning by using a latent representation, temporal graph (TG) instead of reasoning over the original context, they adopt a temporal representation that enhances TR learning. |
| Outcome: | The proposed framework improves the learning of language-based TR by incorporating a latent representation, temporal graph (TG) a synthetic dataset is constructed for fine-tuning LLMs on text-to-TG translation tasks and benchmarks. |