Related papers: SarcasmMiner: A Dual-Track Post-Training Framework…

Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this,…

Sarcasm is common in online discussions, yet difficult for machines to identify because the intended meaning often contradicts the literal wording. In this work, I study sarcasm detection using only classical machine learning methods and…

In the era of large language models (LLMs), the task of ``System I''~-~the fast, unconscious, and intuitive tasks, e.g., sentiment analysis, text classification, etc., have been argued to be successfully solved. However, sarcasm, as a…

Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful…

In recent months, substantial progress has been made in complex reasoning of Large Language Models, particularly through the application of test-time scaling. Notable examples include o1/o3/o4 series and DeepSeek-R1. When responding to a…

Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the multi-scale credit assignment…

Multimodal large language models (MLLMs) often struggle to ground reasoning in perceptual evidence. We present a systematic study of perception strategies-explicit, implicit, visual, and textual-across four multimodal benchmarks and two…

Large Reasoning Models (LRMs) often suffer from overthinking, generating verbose reasoning traces that compromise both computational efficiency and interpretability. Unlike prior efforts that rely on global length-based rewards, we propose…

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global…

Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these…

Sarcasm, a common feature of human communication, poses challenges in interpersonal interactions and human-machine interactions. Linguistic research has highlighted the importance of prosodic cues, such as variations in pitch, speaking…

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, video, and audio data. First, we construct a comprehensive training corpus comprising 181k samples spanning these four modalities. Our…

Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However,…

Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…

Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) often leads to spurious reasoning since only the final-answer…

Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, the speaker's sarcastic intent is not always apparent without additional context. Focusing on social media discussions, we…

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments…

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or statements that…

Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference. Moreover, the mechanisms…