Related papers: Complexity Agnostic Recursive Decomposition of Tho…

We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages…

Repeating a gate sequence multiple times amplifies systematic errors coherently, making it a useful tool for characterizing quantum gates. However, the precision of such an approach is limited by low-frequency noises, while its efficiency…

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…

Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their…

Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers. These reasoning steps greatly improve model interpretability and verification, but objectively…

Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate personalized item sequences. However, their adoption is…

Elaborating a series of intermediate reasoning steps significantly improves the ability of large language models (LLMs) to solve complex problems, as such steps would evoke LLMs to think sequentially. However, human sarcasm understanding is…

Self-Consistency (SC) is an effective decoding strategy that improves the reasoning performance of Large Language Models (LLMs) by generating multiple chain-of-thought reasoning paths and selecting the final answer via majority voting.…

Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving…

Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…

In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair,…

Implicit sentiment analysis aims to uncover emotions that are subtly expressed, often obscured by ambiguity and figurative language. To accomplish this task, large language models and multi-step reasoning are needed to identify those…

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address…

Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people's actions, goals, and mental states. While this task is easy…

Large Language Models have demonstrated remarkable abilities in reasoning and planning by breaking down complex problems into sequential steps. Despite their success in various domains like mathematical problem-solving and coding, LLMs face…

Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the…

We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. ACCORD introduces formal elements to…

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could…

Large Language Models (LLMs) have made substantial progress in recent years, yet evaluating their capabilities in practical Retrieval-Augmented Generation (RAG) scenarios remains challenging. In practical applications, LLMs must demonstrate…

Multi-modal reasoning requires the seamless integration of visual and linguistic cues, yet existing Chain-of-Thought methods suffer from two critical limitations in cross-modal scenarios: (1) over-reliance on single coarse-grained image…