相关论文: Spilling the Beans: Teaching LLMs to Self-Report T…

Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes remain limited. We present a controlled comparison of six…

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…

Large language models (LLMs) are increasingly deployed as "agents" for decision-making (DM) in interactive and dynamic environments. Yet, since they were not originally designed for DM, recent studies show that LLMs can struggle even in…

When transferring a pretrained model to a downstream task, two popular methods are full fine-tuning (updating all the model parameters) and linear probing (updating only the last linear layer -- the "head"). It is well known that…

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Harmful fine-tuning (HFT), performed directly on open-source LLMs or through Fine-tuning-as-a-Service, breaks safety alignment and poses significant threats. Existing methods aim to mitigate HFT risks by learning robust representation on…

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by…

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or…

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples,…

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying training data, for example by adding data that better specify the intended…

Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific…

Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time,…

Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models (LMs) with human preferences post pre-training. While SFT excels in efficiency and PO in effectiveness, they are often combined…

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can…

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…