Related papers: Context-Aware Hierarchical Learning: A Two-Step Pa…
Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…
Hierarchical reinforcement learning (HRL) has seen widespread interest as an approach to tractable learning of complex modular behaviors. However, existing work either assume access to expert-constructed hierarchies, or use…
Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses to identical prompts. This one-size-fits-all mechanism…
Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more…
In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our…
In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks using few examples, with task vectors - specific hidden state activations - hypothesized to encode task information. Existing studies are limited by…
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…
In recent years, large language models (LLMs) have achieved strong performance on benchmark tasks, especially in zero or few-shot settings. However, these benchmarks often do not adequately address the challenges posed in the real-world,…
Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…
Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…
Understanding how large language models (LLMs) acquire, retain, and apply knowledge remains an open challenge. This paper introduces a novel framework, K-(CSA)^2, which categorizes LLM knowledge along two dimensions: correctness and…
Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged…
Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this…
In-context learning (ICL) in Large Language Models (LLMs) has emerged as a powerful new learning paradigm. However, its underlying mechanism is still not well understood. In particular, it is challenging to map it to the "standard" machine…
Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these…
Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description…
Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…
In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and…
We introduce a unified Learning Context (LC) framework designed to transition AI-based education from context-blind mimicry to a principled, holistic understanding of the learner. This white paper provides a multidisciplinary roadmap for…
Large language models (LLMs) are powerful zero- and few-shot learners. However, when predicting over a set of candidate options, LLMs suffer from label biases, and existing calibration methods overlook biases arising from multi-token class…