相关论文: Token Buncher: Shielding LLMs from Harmful Reinfor…

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios.…

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…

Value-based reinforcement learning (RL) can in principle learn effective policies for a wide range of multi-turn problems, from games to dialogue to robotic control, including via offline RL from static previously collected datasets.…

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment…

Reinforcement learning (RL) has been proven to be an effective and robust method for training neural machine translation systems, especially when paired with powerful reward models that accurately assess translation quality. However, most…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and…

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack,…

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…

Fine tuning has been regarded as a de facto approach for adapting large language models (LLMs) to downstream tasks, but the high training memory consumption inherited from LLMs makes this process inefficient. Among existing memory efficient…

As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM…

Reinforcement Learning (RL) has played a central role in the recent surge of LLMs' math abilities by enabling self-improvement through binary verifier signals. In contrast, Supervised Learning (SL) is rarely considered for such…

Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…