LLM Unlearning via Loss Adjustment with Only Forget Data

Unlearning in Large Language Models (LLMs) is essential for ensuring ethical and responsible AI use, especially in addressing privacy leak, bias, safety, and evolving regulations. Existing approaches to LLM unlearning often rely on retain data or a reference LLM, yet they struggle to adequately balance unlearning performance with overall model utility. This challenge arises because leveraging explicit retain data or implicit knowledge of retain data from a reference LLM to fine-tune the model tends to blur the boundaries between the forgotten and retain data, as different queries often elicit similar responses. In this work, we propose eliminating the need to retain data or the reference LLM for response calibration in LLM unlearning. Recognizing that directly applying gradient ascent on the forget data often leads to optimization instability and poor performance, our method guides the LLM on what not to respond to, and importantly, how to respond, based on the forget data. Hence, we introduce Forget data only Loss AjustmenT (FLAT), a "flat" loss adjustment approach which addresses these issues by maximizing f-divergence between the available template answer and the forget answer only w.r.t. the forget data. The variational form of the defined f-divergence theoretically provides a way of loss adjustment by assigning different importance weights for the learning w.r.t. template responses and the forgetting of responses subject to unlearning. Empirical results demonstrate that our approach not only achieves superior unlearning performance compared to existing methods but also minimizes the impact on the model's retained capabilities, ensuring high utility across diverse tasks, including copyrighted content unlearning on Harry Potter dataset and MUSE Benchmark, and entity unlearning on the TOFU dataset.

Improving Data Efficiency via Curating LLM-Driven Rating Systems

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling laws. While LLM-based data quality rating systems offer a cost-effective alternative to human annotation, they often suffer from inaccuracies and biases, even in powerful models like GPT-4. In this work, we introduce DS2, a Diversity-aware Score curation method for Data Selection. By systematically modeling error patterns through a score transition matrix, DS2 corrects LLM-based scores and promotes diversity in the selected data samples. Our approach shows that a curated subset (just 3.3% of the original dataset) outperforms full-scale datasets (300k samples) across various machine-alignment benchmarks, and matches or surpasses human-aligned datasets such as LIMA with the same sample size (1k samples). These findings challenge conventional data scaling assumptions, highlighting that redundant, low-quality samples can degrade performance and reaffirming that "more can be less."

Large Language Model Unlearning via Embedding-Corrupted Prompts

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and efficiently unlearning knowledge from an LLM remains challenging due to the potential collateral damage caused by the fuzzy boundary between retention and forgetting, and the large computational requirements for optimization across state-of-the-art models with hundreds of billions of parameters. In this work, we present Embedding-COrrupted (ECO) Prompts, a lightweight unlearning framework for large language models to address both the challenges of knowledge entanglement and unlearning efficiency. Instead of relying on the LLM itself to unlearn, we enforce an unlearned state during inference by employing a prompt classifier to identify and safeguard prompts to forget. We learn corruptions added to prompt embeddings via zeroth order optimization toward the unlearning objective offline and corrupt prompts flagged by the classifier during inference. We find that these embedding-corrupted prompts not only lead to desirable outputs that satisfy the unlearning objective but also closely approximate the output from a model that has never been trained on the data intended for forgetting. Through extensive experiments on unlearning, we demonstrate the superiority of our method in achieving promising unlearning at nearly zero side effects in general domains and domains closely related to the unlearned ones. Additionally, we highlight the scalability of our method to 100 LLMs, ranging from 0.5B to 236B parameters, incurring no additional cost as the number of parameters increases.

Experimental quantum natural gradient optimization in photonics

Variational quantum algorithms (VQAs) combining the advantages of parameterized quantum circuits and classical optimizers, promise practical quantum applications in the Noisy Intermediate-Scale Quantum era. The performance of VQAs heavily depends on the optimization method. Compared with gradient-free and ordinary gradient descent methods, the quantum natural gradient (QNG), which mirrors the geometric structure of the parameter space, can achieve faster convergence and avoid local minima more easily, thereby reducing the cost of circuit executions. We utilized a fully programmable photonic chip to experimentally estimate the QNG in photonics for the first time. We obtained the dissociation curve of the He-H$^+$ cation and achieved chemical accuracy, verifying the outperformance of QNG optimization on a photonic device. Our work opens up a vista of utilizing QNG in photonics to implement practical near-term quantum applications.

Quantum generative adversarial learning in photonics

Quantum Generative Adversarial Networks (QGANs), an intersection of quantum computing and machine learning, have attracted widespread attention due to their potential advantages over classical analogs. However, in the current era of Noisy Intermediate-Scale Quantum (NISQ) computing, it is essential to investigate whether QGANs can perform learning tasks on near-term quantum devices usually affected by noise and even defects. In this Letter, using a programmable silicon quantum photonic chip, we experimentally demonstrate the QGAN model in photonics for the first time, and investigate the effects of noise and defects on its performance. Our results show that QGANs can generate high-quality quantum data with a fidelity higher than 90\%, even under conditions where up to half of the generator's phase shifters are damaged, or all of the generator and discriminator's phase shifters are subjected to phase noise up to 0.04$\pi$. Our work sheds light on the feasibility of implementing QGANs on NISQ-era quantum hardware.

Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learning

Inspired by expert evaluation policy for urban perception, we proposed a novel inverse reinforcement learning (IRL) based framework for predicting urban safety and recovering the corresponding reward function. We also presented a scalable state representation method to model the prediction problem as a Markov decision process (MDP) and use reinforcement learning (RL) to solve the problem. Additionally, we built a dataset called SmallCity based on the crowdsourcing method to conduct the research. As far as we know, this is the first time the IRL approach has been introduced to the urban safety perception and planning field to help experts quantitatively analyze perceptual features. Our results showed that IRL has promising prospects in this field. We will later open-source the crowdsourcing data collection site and the model proposed in this paper.