Abstract:In the recent development of AI reasoning, large language models (LLMs) are trained to automatically generate chain-of-thought reasoning steps, which have demonstrated compelling performance on math and coding tasks. However, when bias is mixed within the reasoning process to form strong logical arguments, it could cause even more harmful results and further induce hallucinations. In this paper, we have evaluated the 8B and 32B variants of DeepSeek-R1 against their instruction tuned counterparts on the BBQ dataset, and investigated the bias that is elicited out and being amplified through reasoning steps. To the best of our knowledge, this empirical study is the first to assess bias issues in LLM reasoning.
Abstract:Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process into the LLM itself through process rewards as feedback and achieved improvements over prompting strategies. Due to the cost of step-level annotation, some turn to outcome rewards as feedback. Aside from these training-based approaches, training-free techniques leverage frozen LLMs or external tools for feedback at each step to enhance the reasoning process. With the abundance of work in mathematics due to its logical nature, we present a survey of strategies utilizing feedback at the step and outcome levels to enhance multi-step math reasoning for LLMs. As multi-step reasoning emerges a crucial component in scaling LLMs, we hope to establish its foundation for easier understanding and empower further research.
Abstract:A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a significant domain gap between the modalities of vision and language, especially when training data is scarce in few-shot settings, where only very limited data are available for training. In order to mitigate this issue, a multi-modal meta-learning framework has been proposed to bridge the gap between two frozen pretrained large vision and language models by introducing a tunable prompt connecting these two large models. For few-shot image captioning, the existing multi-model meta-learning framework utilizes a one-step prompting scheme to accumulate the visual features of input images to guide the language model, which struggles to generate accurate image descriptions with only a few training samples. Instead, we propose a chain-of-thought (CoT) meta-learning scheme as a multi-step image captioning procedure to better imitate how humans describe images. In addition, we further propose to learn different meta-parameters of the model corresponding to each CoT step in distinct subspaces to avoid interference. We evaluated our method on three commonly used image captioning datasets, i.e., MSCOCO, Flickr8k, and Flickr30k, under few-shot settings. The results of our experiments indicate that our chain-of-thought subspace meta-learning strategy is superior to the baselines in terms of performance across different datasets measured by different metrics.
Abstract:The rapid development of Multimodal Large Language Models (MLLMs) has enabled the integration of multiple modalities, including texts and images, within the large language model (LLM) framework. However, texts and images are usually interconnected, forming a multimodal attributed graph (MMAG). It is underexplored how MLLMs can incorporate the relational information (\textit{i.e.}, graph structure) and semantic information (\textit{i.e.,} texts and images) on such graphs for multimodal comprehension and generation. In this paper, we propose GraphGPT-o, which supports omni-multimodal understanding and creation on MMAGs. We first comprehensively study linearization variants to transform semantic and structural information as input for MLLMs. Then, we propose a hierarchical aligner that enables deep graph encoding, bridging the gap between MMAGs and MLLMs. Finally, we explore the inference choices, adapting MLLM to interleaved text and image generation in graph scenarios. Extensive experiments on three datasets from different domains demonstrate the effectiveness of our proposed method. Datasets and codes will be open-sourced upon acceptance.
Abstract:While recent advancements in aligning Large Language Models (LLMs) with recommendation tasks have shown great potential and promising performance overall, these aligned recommendation LLMs still face challenges in complex scenarios. This is primarily due to the current alignment approach focusing on optimizing LLMs to generate user feedback directly, without incorporating deliberation. To overcome this limitation and develop more reliable LLMs for recommendations, we propose a new Deliberative Recommendation task, which incorporates explicit reasoning about user preferences as an additional alignment goal. We then introduce the Deliberative User Preference Alignment framework, designed to enhance reasoning capabilities by utilizing verbalized user feedback in a step-wise manner to tackle this task. The framework employs collaborative step-wise experts and tailored training strategies for each expert. Experimental results across three real-world datasets demonstrate the rationality of the deliberative task formulation and the superior performance of the proposed framework in improving both prediction accuracy and reasoning quality.
Abstract:The growing importance of textual and relational systems has driven interest in enhancing large language models (LLMs) for graph-structured data, particularly Text-Attributed Graphs (TAGs), where samples are represented by textual descriptions interconnected by edges. While research has largely focused on developing specialized graph LLMs through task-specific instruction tuning, a comprehensive benchmark for evaluating LLMs solely through prompt design remains surprisingly absent. Without such a carefully crafted evaluation benchmark, most if not all, tailored graph LLMs are compared against general LLMs using simplistic queries (e.g., zero-shot reasoning with LLaMA), which can potentially camouflage many advantages as well as unexpected predicaments of them. To achieve more general evaluations and unveil the true potential of LLMs for graph tasks, we introduce Graph In-context Learning (GraphICL) Benchmark, a comprehensive benchmark comprising novel prompt templates designed to capture graph structure and handle limited label knowledge. Our systematic evaluation shows that general-purpose LLMs equipped with our GraphICL outperform state-of-the-art specialized graph LLMs and graph neural network models in resource-constrained settings and out-of-domain tasks. These findings highlight the significant potential of prompt engineering to enhance LLM performance on graph learning tasks without training and offer a strong baseline for advancing research in graph LLMs.
Abstract:Recommender systems remain an essential topic due to its wide application in various domains and the business potential behind them. With the rise of deep learning, common solutions have leveraged neural networks to facilitate collaborative filtering, and some have turned to generative adversarial networks to augment the dataset and tackle the data sparsity issue. However, they are limited in learning the complex user and item distribution and still suffer from model collapse. Given the great generation capability exhibited by diffusion models in computer vision recently, many recommender systems have adopted diffusion models and found improvements in performance for various tasks. Diffusion models in recommender systems excel in managing complex user and item distributions and do not suffer from mode collapse. With these advantages, the amount of research in this domain have been growing rapidly and calling for a systematic survey. In this survey paper, we present and propose a taxonomy on past research papers in recommender systems that utilize diffusion models. Distinct from a prior survey paper that categorizes based on the role of the diffusion model, we categorize based on the recommendation task at hand. The decision originates from the rationale that after all, the adoption of diffusion models is to enhance the recommendation performance, not vice versa: adapting the recommendation task to enable diffusion models. Nonetheless, we offer a unique perspective for diffusion models in recommender systems complementary to existing surveys. We present the foundation algorithms in diffusion models and their applications in recommender systems to summarize the rapid development in this field. Finally, we discuss open research directions to prepare and encourage further efforts to advance the field. We compile the relevant papers in a public GitHub repository.
Abstract:Since the launch of ChatGPT in late 2022, the capacities of Large Language Models and their evaluation have been in constant discussion and evaluation both in academic research and in the industry. Scenarios and benchmarks have been developed in several areas such as law, medicine and math (Bommasani et al., 2023) and there is continuous evaluation of model variants. One area that has not received sufficient scenario development attention is journalism, and in particular journalistic sourcing and ethics. Journalism is a crucial truth-determination function in democracy (Vincent, 2023), and sourcing is a crucial pillar to all original journalistic output. Evaluating the capacities of LLMs to annotate stories for the different signals of sourcing and how reporters justify them is a crucial scenario that warrants a benchmark approach. It offers potential to build automated systems to contrast more transparent and ethically rigorous forms of journalism with everyday fare. In this paper we lay out a scenario to evaluate LLM performance on identifying and annotating sourcing in news stories on a five-category schema inspired from journalism studies (Gans, 2004). We offer the use case, our dataset and metrics and as the first step towards systematic benchmarking. Our accuracy findings indicate LLM-based approaches have more catching to do in identifying all the sourced statements in a story, and equally, in matching the type of sources. An even harder task is spotting source justifications.
Abstract:We present a comprehensive theoretical framework analyzing the relationship between data distributions and fairness guarantees in equitable deep learning. Our work establishes novel theoretical bounds that explicitly account for data distribution heterogeneity across demographic groups, while introducing a formal analysis framework that minimizes expected loss differences across these groups. We derive comprehensive theoretical bounds for fairness errors and convergence rates, and characterize how distributional differences between groups affect the fundamental trade-off between fairness and accuracy. Through extensive experiments on diverse datasets, including FairVision (ophthalmology), CheXpert (chest X-rays), HAM10000 (dermatology), and FairFace (facial recognition), we validate our theoretical findings and demonstrate that differences in feature distributions across demographic groups significantly impact model fairness, with performance disparities particularly pronounced in racial categories. The theoretical bounds we derive crroborate these empirical observations, providing insights into the fundamental limits of achieving fairness in deep learning models when faced with heterogeneous data distributions. This work advances our understanding of fairness in AI-based diagnosis systems and provides a theoretical foundation for developing more equitable algorithms. The code for analysis is publicly available via \url{https://github.com/Harvard-Ophthalmology-AI-Lab/fairness_guarantees}.
Abstract:Recent progress in generative AI, especially diffusion models, has demonstrated significant utility in text-to-image synthesis. Particularly in healthcare, these models offer immense potential in generating synthetic datasets and training medical students. However, despite these strong performances, it remains uncertain if the image generation quality is consistent across different demographic subgroups. To address this critical concern, we present the first comprehensive study on the fairness of medical text-to-image diffusion models. Our extensive evaluations of the popular Stable Diffusion model reveal significant disparities across gender, race, and ethnicity. To mitigate these biases, we introduce FairDiffusion, an equity-aware latent diffusion model that enhances fairness in both image generation quality as well as the semantic correlation of clinical features. In addition, we also design and curate FairGenMed, the first dataset for studying the fairness of medical generative models. Complementing this effort, we further evaluate FairDiffusion on two widely-used external medical datasets: HAM10000 (dermatoscopic images) and CheXpert (chest X-rays) to demonstrate FairDiffusion's effectiveness in addressing fairness concerns across diverse medical imaging modalities. Together, FairDiffusion and FairGenMed significantly advance research in fair generative learning, promoting equitable benefits of generative AI in healthcare.