相关论文: Assistive Recipe Editing through Critiquing

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and…

Conversational search aims to satisfy users' complex information needs via multiple-turn interactions. The key challenge lies in revealing real users' search intent from the context-dependent queries. Previous studies achieve conversational…

Modern recommender systems place great inclination towards facilitating user experience, as more applications enabling users to critique and then refine recommendations immediately. Considering the real-time requirements, critique-able…

Conventional machine learning pipelines often struggle to recognize categories absent from the original trainingset. This gap typically reduces accuracy, as fixed datasets rarely capture the full diversity of a domain. To address this, we…

Meal recommendation, as a typical health-related recommendation task, contains complex relationships between users, courses, and meals. Among them, meal-course affiliation associates user-meal and user-course interactions. However, an…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While…

We investigate the problem of online collaborative filtering under no-repetition constraints, whereby users need to be served content in an online fashion and a given user cannot be recommended the same content item more than once. We start…

Recent studies have shown that providing personalized explanations alongside recommendations increases trust and perceived quality. Furthermore, it gives users an opportunity to refine the recommendations by critiquing parts of the…

High-quality and carefully curated data is a cornerstone of training medical large language models, as it directly impacts both generalization and robustness to unseen clinical tasks. We investigate strategies for training and data curation…

Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically comprehend explicit and specific instructions. However, they…

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is…

We propose a novel alignment mechanism to deal with procedural reasoning on a newly released multimodal QA dataset, named RecipeQA. Our model is solving the textual cloze task which is a reading comprehension on a recipe containing images…

Large Language Models (LLMs) are widely used to support software developers in tasks such as code generation, optimization, and documentation. However, their ability to improve existing programming answers in a human-like manner remains…

Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge.…

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due…

Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in…

The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large Multimodal Models (LMMs) remains underexplored despite their…