相关论文: Beyond Hidden-Layer Manipulation: Semantically-Awa…

When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language? We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate natural-language…

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge for existing Speech Large Language Models (Speech LLMs). While these models excel at general…

Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens from a fully masked sequence. Their standard confidence-based unmasking strategy systematically defers high-entropy logical connective tokens, degrading…

Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems. However, some differentiable operators could bring a significant bias…

Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework…

Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-step reasoning chains,…

Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems. However, click interactions inherently contain substantial noise, including accidental clicks, clickbait-induced interactions, and…

While Vision-Language Models (VLMs) have achieved remarkable performance across diverse downstream tasks, recent studies have shown that they can inherit social biases from the training data and further propagate them into downstream…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance.…

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual…

Detecting deception in an increasingly digital world is both a critical and challenging task. In this study, we present a comprehensive evaluation of the automated deception detection capabilities of Large Language Models (LLMs) and Large…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

In previous studies on knowledge distillation, the significance of logit distillation has frequently been overlooked. To revitalize logit distillation, we present a novel perspective by reconsidering its computation based on the semantic…

Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs'…

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…