Related papers: From Prediction to Justification: Aligning Sentime…

Robust perception and reasoning require consistency across sensory modalities. Yet current multimodal models often violate this principle, yielding contradictory predictions for visual and textual representations of the same concept. Rather…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

In the era of rapid evolution of generative language models within the realm of natural language processing, there is an imperative call to revisit and reformulate evaluation methodologies, especially in the domain of aspect-based sentiment…

As an extensive research in the field of natural language processing (NLP), aspect-based sentiment analysis (ABSA) is the task of predicting the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most…

Aspect-Based Sentiment Analysis (ABSA) involves extracting opinions from textual data about specific entities and their corresponding aspects through various complementary subtasks. Several prior research has focused on developing ad hoc…

As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been attracting considerable interest in the last decade. To handle…

Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we…

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…

We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an important role in CQA, where user intent evolves across dialogue turns, and utterances are often…

Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence. While state-of-the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue…

An important aspect of human conversation difficult for machines is conversing with empathy, which is to understand the user's emotion and respond appropriately. Recent neural conversation models that attempted to generate empathetic…

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate…

Leveraging multimodal large models for image segmentation has become a prominent research direction. However, existing approaches typically rely heavily on manually annotated datasets that include explicit reasoning processes, which are…

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize…

We introduce InstructABSA, an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model…