Related papers: Yes FLoReNce, I Will Do Better Next Time! Agentic …

Effective feedback, including critique and evaluation, helps designers develop design concepts and refine their ideas, supporting informed decision-making throughout the iterative design process. However, in studio-based design courses,…

Individuals express diverse opinions, a fair summary should represent these viewpoints comprehensively. Previous research on fairness in opinion summarisation using large language models (LLMs) relied on hyperparameter tuning or providing…

This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i.e., one system per user query. Our core idea is to incentivize a reasoning-based meta-agent via external execution…

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph…

This study investigates the use of prompt engineering to enhance large language models (LLMs), specifically GPT-4o-mini and gemini-1.5-flash, in sentiment analysis tasks. It evaluates advanced prompting techniques like few-shot learning,…

Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-modal reasoning remains underexplored, with conflicting reports on whether added modalities help or…

Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among…

Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of large language models (LLMs), a phenomenon we term…

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity.…

Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potential for explainability. However, naively applying those MLLMs…

Large Language Models (LLMs) are recruited in applications that span from clinical assistance and legal support to question answering and education. Their success in specialized tasks has led to the claim that they possess human-like…

Recent advances in large language models (LLMs) have enabled more semantic-aware recommendations through natural language generation. Existing LLM for recommendation (LLM4Rec) methods mostly operate in a System 1-like manner, relying on…

Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…

We present HumorBench, a benchmark designed to evaluate large language models' (LLMs) ability to reason about and explain sophisticated humor in cartoon captions. As reasoning models increasingly saturate existing benchmarks in mathematics…

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activations more interpretable by exposing latent features that often…

Hateful memes often require compositional multimodal reasoning: the image and text may appear benign in isolation, yet their interaction conveys harmful intent. Although thinking-based multimodal large language models (MLLMs) have recently…

Large language models (LLMs) have achieved remarkable performance in generating human-like text and solving reasoning tasks of moderate complexity, such as question-answering and mathematical problem-solving. However, their capabilities in…

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

Memes are a dominant medium for online communication and manipulation because meaning emerges from interactions between embedded text, imagery, and cultural context. Existing meme research is distributed across tasks (hate, misogyny,…

System Instructions (SIs), or system prompts, are pivotal for guiding Large Language Models (LLMs) but manual crafting is resource-intensive and often suboptimal. Existing automated methods frequently generate non-human-readable "soft…