Related papers: Agentic Knowledge Distillation: Autonomous Trainin…

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by…

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Corpus distillation for biomedical large language models (LLMs) seeks to address the pressing challenge of insufficient quantity and quality in open-source annotated scientific corpora, which remains a bottleneck for effective LLM training…

Large language models (LLMs) exhibit strong capabilities as decision-making agents by interleaving reasoning and actions, as seen in ReAct-style frameworks. Yet, their practical deployment is constrained by high inference costs and large…

Phishing websites remain a significant cybersecurity threat, necessitating accurate and cost-effective detection mechanisms. In this paper, we present CLASP, a novel system that effectively identifies phishing websites by leveraging…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

Recent studies have demonstrated the great potential of Large Language Models (LLMs) serving as zero-shot relevance rankers. The typical approach involves making comparisons between pairs or lists of documents. Although effective, these…

Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training…

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Phishing attacks represent a significant cybersecurity threat, necessitating adaptive detection techniques. This study explores few-shot Adaptive Linguistic Prompting (ALP) in detecting phishing webpages through the multimodal capabilities…

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

This paper explores the use of Large Language Models (LLMs) in spear phishing message generation and evaluates their performance compared to human-authored counterparts. Our pilot study examines the effectiveness of smishing (SMS phishing)…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…