FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models

Challenge:	FairCoT enhances fairness in text-to-image generative models by integrating iterative reasoning . experimental evaluations demonstrate FairCot significantly enhances diversity without sacrificing image quality or semantic fidelity.
Approach:	FairCoT is a framework that enhances fairness in text-to-image generative models . it employs iterative CoT refinement to mitigate biases and dynamically adjusts textual prompts .
Outcome:	FairCoT combines iterative CoT refinement with iterating reasoning processes . it addresses limitations of zero-shot CoT in sensitive scenarios, authors say .

Similar Papers

Overview

Challenge

Approach

Outcome

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs (2025.acl-long)

Copied to clipboard

Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao

Responsible & Trustworthy NLP

Challenge:	Existing approaches to continuous-space reasoning focus on hard token decoding and suffer from catastrophic forgetting.
Approach:	They propose a method that generates instance-specific soft thought tokens as the initial chain of thoughts and maps them into the LLM’s representation space via a trainable projection module.
Outcome:	The proposed method improves LLM reasoning performance through supervised, parameter-efficient fine-tuning.

FedCoT: Federated Chain-of-Thought Distillation for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Tao Fan, Weijing Chen, Yan Kang, Guoqiang Ma, Hanlin Gu, Yuanfeng Song, Lixin Fan, Qiang Yang

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks.
Approach:	They propose a federated framework for the Chain-of-Thought distillation of knowledge from LLMs to SLMs, while adhering to privacy requirements.
Outcome:	The proposed framework ensures secure knowledge transfer from an LLM on a high-powered server to an SLM on resource-constrained client while adhering to privacy requirements.

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)

Copied to clipboard

Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Zheng Wei, Yang Tang

Language Models

Challenge:	Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain.
Approach:	They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable.
Outcome:	The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting.

Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs (2026.acl-long)

Copied to clipboard

Qihua Dong, Yitian Zhang, Huimin Zeng, Yizhou Wang, Jianglin Lu, Kuo Yang, Yun Fu

Multimodality

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have shifted visual reasoning from tool-calling to end-to-end perceptionreasoning.
Approach:	They synthesize the emerging paradigm of Image-Grounded Chain-of-Thought (IG-CoT) they propose a method-centric taxonomy covering prompting, supervised fine-tuning, and reinforcement learning .
Outcome:	The proposed model is based on a method-centric taxonomy and benchmarks.

How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? (2022.emnlp-main)

Copied to clipboard

Hritik Bansal, Da Yin, Masoud Monajatipoor, Kai-Wei Chang

Responsible & Trustworthy NLP

Challenge:	Text-to-image generative models can generate high-quality photo-realistic images conditional on natural language text descriptions in a zero-shot fashion.
Approach:	They propose an Ethical NaTural Language Interventions in Text-to-Image GENeration benchmark dataset to evaluate the change in image generation conditional on ethical interventions across three social axes – gender, skin color, and culture.
Outcome:	The proposed model generations cover diverse social groups while preserving image quality.

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Shidong Cao, Hongzhan Lin, Yuxuan Gu, Ziyang Luo, Jing Ma

Reasoning

Challenge:	Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but is vulnerable to exposure bias and error accumulation.
Approach:	They propose a diffusion-styled CoT framework that reformulates CoT reasoning as an iterative denoising process.
Outcome:	The proposed framework outperforms existing methods on three multi-step CoT reasoning benchmarks.

FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance (2025.emnlp-main)

Copied to clipboard

Mintong Kang, Vinayshekhar Bannihatti Kumar, Shamik Roy, Abhishek Kumar, Sopan Khosla, Balakrishnan Murali Narayanaswamy, Rashmi Gangadharaiah

Responsible & Trustworthy NLP

Challenge:	Text-to-image diffusion models often exhibit generation biases toward specific demographic groups, raising ethical concerns and limiting their adoption.
Approach:	They propose an adaptive latent guidance mechanism which controls the generation distribution during inference by dynamically adjusting the diffusion process to enforce specific attributes.
Outcome:	The proposed model outperforms existing models on HBE and Stable Bias datasets and achieves substantial bias reduction.

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs (2025.acl-long)

Copied to clipboard

Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych

Language Models

Challenge:	Existing approaches to generate multiple independent CoTs, combining them through ensembling or other post-hoc strategies, have been shown to be effective in boosting performance.
Approach:	They propose a method where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.
Outcome:	The proposed model can generate multiple chains of thought within a single inference step without external feedback.

Content-Specific Humorous Image Captioning Using Incongruity Resolution Chain-of-Thought (2024.findings-naacl)

Copied to clipboard

Kohtaro Tanaka, Kohei Uehara, Lin Gu, Yusuke Mukuta, Tatsuya Harada

Multimodality

Challenge:	Existing methods for generating humorous captions are generic and do not capture the content of images.
Approach:	They propose a framework that generates content-specific resolutions from fine details extracted from an image and integrates logit bias and negative sampling to suppress the output of generic resolutions.
Outcome:	The proposed framework generates humorous captions tailored to the content of specific input images.

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks (2023.emnlp-main)

Copied to clipboard

Hoang Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, Philip Yu

Semantic Text Processing

Challenge:	Chain-of-Thought prompting is popular in reasoning tasks, but its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.
Approach:	They propose a Coarse-to-Fine Chain-of-Thought approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire essential concepts.
Outcome:	The proposed approach is effective in assisting the LLMs adapt to multi-grained NLU tasks under zero-shot and few-shot multi-domain settings.