Papers with COT
C2DLM: Causal Concept-Guided Diffusion Large Language Models (2026.findings-acl)
Copied to clipboard
Kairong Han, Nuanqiao Shan, Ziyu Zhao, Zijing Hu, Xinpeng Dong, Ye Jun Jian, Lujia Pan, Fei Wu, Kun Kuang
| Challenge: | Autoregressive (AR) and diffusion language models (DLMs) suffer from insufficient reasoning capabilities. |
| Approach: | They propose a fully connected Diffusion Language Model that uses a concept-level causal graph to guide attention to learn causal relationships between concepts. |
| Outcome: | The proposed model achieves a 12% improvement and 3.2 training speedup on the COT-OrderPerturb task, along with an average gain of 1.31% across six downstream reasoning tasks. |
Enhancing Online Recruitment with Category-Aware MoE and LLM-based Data Augmentation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to measure the matching degree of a job and a candidate face several challenges, such as low-quality job descriptions and similar candidate-job pairs. |
| Approach: | They propose a large language model-based method that polishes and rewrites low-quality job descriptions by leveraging chain-of-thought prompts and category-aware Mixture of Experts (MoE) module incorporates category embeddings to dynamically assign weights to the experts and learns more distinguishable patterns for similar candidate-job pairs. |
| Outcome: | The proposed method surpasses existing methods by 2.40% in AUC and 7.46% in GAUC and boosts click-through conversion rate (CTCVR) by 19.4% in online tests, saving millions of CNY in external headhunting expenses. |
Program-Aided Reasoners (Better) Know What They Know (2024.naacl-long)
Copied to clipboard
| Challenge: | Prior work shows that program-aided reasoning improves accuracy but also requires reasoners to "know what they know". |
| Approach: | They compare the calibration of program-aided language models (PAL) and text-based Chain-of-thought (COT) prompting techniques over 5 datasets and 2 model types . |
| Outcome: | The proposed methods improve accuracy and calibrate the models over 5 datasets and 2 model types. |
Zero-Shot Cross-Domain Aspect-Based Sentiment Analysis via Domain-Contextualized Chain-of-Thought Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Cross-domain aspect-based sentiment analysis (ABSA) aims to learn specific knowledge from a source domain to perform various tasks on a target domain. |
| Approach: | a new framework is proposed to learn specific knowledge from a source domain . the framework uses domain adaptation techniques to transfer domain-agnostic features . |
| Outcome: | a new learning framework for cross-domain aspect-based sentiment analysis is proposed . it effectively eliminates dependency on target-domain annotations, authors say . |
Chain-of-Thought Embeddings for Stance Detection on Social Media (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Stance detection on social media platforms like Twitter is challenging for Large Language Models (LLMs), as emerging slang and colloquial language in online conversations often contain deeply implicit stance labels. |
| Approach: | They propose to embed COT reasonings into a traditional RoBERTa-based stance detection pipeline by embedding COT stance reasonings and integrating them into slang-based models. |
| Outcome: | The proposed model achieves SOTA performance on multiple stance detection datasets collected from social media. |
SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on the vulnerability of large language models to SQL injection have been limited. |
| Approach: | They propose to evaluate the potential of language models to leak sensitive data when generating SQL queries. |
| Outcome: | The proposed model with the best performance has an accuracy of 61.7%, compared to humans who achieve 94% accuracy. |
RippleCOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | et al., 2022: ripple effect challenges knowledge editing for large language models. |
| Approach: | They propose a method to improve the accuracy of large language models by integrating Chain-of-Thought reasoning into the ICL editing approach. |
| Outcome: | RIPPLE-COT outperforms the state-of-the-art on the ripple effect, with gains ranging from 7.8% to 87.1%. |
It’s Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent research aims to unlock the reasoning capabilities of large language models (LLMs) chain-of-thought (COT) prompting can help LLMs reason toward correct answers, but its efficacy in reasoning toward incorrect answers is unexplored. |
| Approach: | They propose a task where large language models reason toward incorrect answers using chain-of-thought prompting. |
| Outcome: | The proposed task underperforms the strategy of choosing the correct answer on commonsense and scientific reasoning datasets. |
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2025.acl-long)
Copied to clipboard
| Challenge: | MM-Verifier and MM Reasoner are a powerful multimodal reasoning model . large language models (LLMs) have demonstrated exceptional performance across tasks spanning myriad domains. |
| Approach: | They propose a method which combines tree search and verification to generate high-quality chain-of-thought data. |
| Outcome: | The proposed method outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. |
Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to evaluate ChatGPT's causal reasoning abilities are based on pre-trained language models, but they rely on supervised training. |
| Approach: | They conduct the first comprehensive evaluation of ChatGPT’s causal reasoning capabilities using four state-of-the-art (STA) simulations. |
| Outcome: | The proposed model is not a good causal reasoner, but a great causal interpreter. |
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text. |
| Approach: | They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting . |
| Outcome: | The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks. |
Exploring Paraphrasing Strategies for CEFR A1-Level Constraints in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study compares prompt engineering approaches to rephrase general-domain texts . it compares 4 approaches to meet CEFR A1-level constraints in english and italian . |
| Approach: | They compare prompt engineering approaches to rephrase general-domain texts to meet CEFR A1-level constraints in English and Italian. |
| Outcome: | The proposed approaches meet CEFR A1-level constraints in English and Italian. |
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)
Copied to clipboard
Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Z.y. Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, Bo Zheng
| Challenge: | Recent advances in o1-like models have generated long Chain-of-Thought reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs). |
| Approach: | They propose a DeltaBench to analyze the quality and effectiveness of o1-like models and measure their ability to detect errors in long COT reasoning. |
| Outcome: | The proposed model can detect errors in long COT reasoning. |
OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing distributed training frameworks are plagued by over-reliance on prior profiling and poor generalization across models/hardware. |
| Approach: | They propose a model-driven multi-agent framework that leverages Large Language Models to enable automatic and explainable distributed training strategy configuration. |
| Outcome: | The proposed framework outperforms expert-designed training strategies within 20 iterations. |