Deep learning still struggles with certain kinds of scientific data. Notably, pretraining data may not provide coverage of relevant distribution shifts (e.g., shifts induced via the use of different measurement instruments). We consider deep learning models trained to classify the synthesis conditions of uranium ore concentrates (UOCs) and show that model editing is particularly effective for improving generalization to distribution shifts common in this domain. In particular, model editing outperforms finetuning on two curated datasets comprising of micrographs taken of U$_{3}$O$_{8}$ aged in humidity chambers and micrographs acquired with different scanning electron microscopes, respectively.
Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor mitigation approach via machine unlearning to counter such backdoor attacks. The proposed method utilizes model activation of domain-equivalent unseen data to guide the editing of the model's weights. Unlike the previous unlearning-based mitigation methods, ours is computationally inexpensive and achieves state-of-the-art performance while only requiring a handful of unseen samples for unlearning. In addition, we also point out that unlearning the backdoor may cause the whole targeted class to be unlearned, thus introducing an additional repair step to preserve the model's utility after editing the model. Experiment results show that the proposed method is effective in unlearning the backdoor on different datasets and trigger patterns.
Large language models (LLMs) require continual knowledge updates to stay abreast of the ever-changing world facts, prompting the formulation of lifelong model editing task. While recent years have witnessed the development of various techniques for single and batch editing, these methods either fail to apply or perform sub-optimally when faced with lifelong editing. In this paper, we introduce LEMoE, an advanced Mixture of Experts (MoE) adaptor for lifelong model editing. We first analyze the factors influencing the effectiveness of conventional MoE adaptor in lifelong editing, including catastrophic forgetting, inconsistent routing and order sensitivity. Based on these insights, we propose a tailored module insertion method to achieve lifelong editing, incorporating a novel KV anchor routing to enhance routing consistency between training and inference stage, along with a concise yet effective clustering-based editing order planning. Experimental results demonstrate the effectiveness of our method in lifelong editing, surpassing previous model editing techniques while maintaining outstanding performance in batch editing task. Our code will be available.
The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky -- perhaps unsurprisingly, since model editing is essentially belief revision, a storied problem in philosophy that has eluded succinct solutions for decades. Model editing nonetheless demands a solution, since we need to be able to control the knowledge within language models. With this goal in mind, this paper critiques the standard formulation of the model editing problem and proposes a formal testbed for model editing research. We first describe 12 open problems with model editing, based on challenges with (1) defining the problem, (2) developing benchmarks, and (3) assuming LLMs have editable beliefs in the first place. Many of these challenges are extremely difficult to address, e.g. determining far-reaching consequences of edits, labeling probabilistic entailments between facts, and updating beliefs of agent simulators. Next, we introduce a semi-synthetic dataset for model editing based on Wikidata, where we can evaluate edits against labels given by an idealized Bayesian agent. This enables us to say exactly how belief revision in language models falls short of a desirable epistemic standard. We encourage further research exploring settings where such a gold standard can be compared against. Our code is publicly available at: https://github.com/peterbhase/LLM-belief-revision
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domain risks Catastrophic Forgetting (CF). To address this, Lifelong Learning (LLL) algorithms have been proposed for ASR. Prior research has explored techniques such as Elastic Weight Consolidation, Knowledge Distillation, and Replay, all of which necessitate either additional parameters or access to prior domain data. We propose Sequential Model Editing as a novel method to continually learn new domains in ASR systems. Different than previous methods, our approach does not necessitate access to prior datasets or the introduction of extra parameters. Our study demonstrates up to 15% Word Error Rate Reduction (WERR) over fine-tuning baseline, and superior efficiency over other LLL techniques on CommonVoice English multi-accent dataset.
Large language models (LLMs) have demonstrated remarkable capabilities, but updating their knowledge post-training remains a critical challenge. While recent model editing techniques like Rank-One Model Editing (ROME) show promise, their effectiveness may vary based on the nature of the knowledge being edited. We introduce the concept of ``perplexingness'': the degree to which new knowledge conflicts with an LLM's learned conceptual hierarchies and categorical relationships. For instance, editing ``British Shorthair is a kind of cat'' to ``British Shorthair is a kind of dog'' represents a low-perplexingness edit within the same taxonomic level, while editing ``A cat is a kind of animal'' to ``A cat is a kind of plant'' represents a high-perplexingness edit that violates fundamental categorical boundaries. To systematically investigate this phenomenon, we introduce HierarchyData, a carefully curated dataset of 99 hyponym-hypernym pairs across diverse categories. Through controlled experiments across three models and four editing methods, we demonstrate a strong negative correlation between the perplexingness of new knowledge and the effectiveness of knowledge editing. Our analysis reveals that edits involving more abstract concepts (hypernyms) generally exhibit higher perplexingness and are more resistant to modification than their specific counterparts (hyponyms). These findings highlight a fundamental challenge in LLM knowledge editing: the more a new fact contradicts an LLM's learned conceptual hierarchies, the harder it becomes to reliably encode that knowledge.
We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic dimension of the model's features) can be used to assess a model's editability and reveals its previously unrecognised susceptibility to malicious stealth attacks. This metric is fundamental to predicting the success of a variety of editing approaches, and reveals new bridges between disparate families of editing methods. We collectively refer to these as stealth editing methods, because they directly update a model's weights to specify its response to specific known hallucinating prompts without affecting other model behaviour. By carefully applying our theoretical insights, we are able to introduce a new jet-pack network block which is optimised for highly selective model editing, uses only standard network operations, and can be inserted into existing networks. We also reveal the vulnerability of language models to stealth attacks: a small change to a model's weights which fixes its response to a single attacker-chosen prompt. Stealth attacks are computationally simple, do not require access to or knowledge of the model's training data, and therefore represent a potent yet previously unrecognised threat to redistributed foundation models. Extensive experimental results illustrate and support our methods and their theoretical underpinnings. Demos and source code are available at https://github.com/qinghua-zhou/stealth-edits.
The integration of pretrained language models (PLMs) like BERT and GPT has revolutionized NLP, particularly for English, but it has also created linguistic imbalances. This paper strategically identifies the need for linguistic equity by examining several knowledge editing techniques in multilingual contexts. We evaluate the performance of models such as Mistral, TowerInstruct, OpenHathi, Tamil-Llama, and Kan-Llama across languages including English, German, French, Italian, Spanish, Hindi, Tamil, and Kannada. Our research identifies significant discrepancies in normal and merged models concerning cross-lingual consistency. We employ strategies like 'each language for itself' (ELFI) and 'each language for others' (ELFO) to stress-test these models. Our findings demonstrate the potential for LLMs to overcome linguistic barriers, laying the groundwork for future research in achieving linguistic inclusivity in AI technologies.
Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. Among them, ROME is particularly concerning, as it could disrupt LLMs with only a single edit. In this paper, we study the root causes of such collapse. Through extensive analysis, we identify two primary factors that contribute to the collapse: i) inconsistent handling of prefixed and unprefixed keys in the parameter update equation may result in very small denominators, causing excessively large parameter updates; ii) the subject of collapse cases is usually the first token, whose unprefixed key distribution significantly differs from the prefixed key distribution in autoregressive transformers, causing the aforementioned issue to materialize. To validate our findings, we propose a simple yet effective approach: uniformly using prefixed keys during editing phase and adding prefixes during testing phase to ensure the consistency between training and testing. The experimental results show that the proposed solution can prevent model collapse while maintaining the effectiveness of the edits.
Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset scrubbing, or model filtering through unlearning and model editing, which can be bypassed through extraction attacks. We propose REVS, a novel non-gradient-based method for unlearning sensitive information from LMs. REVS identifies and modifies a small subset of neurons relevant for constituent tokens which form sensitive information. To adequately evaluate our method on truly sensitive information, we curate two datasets: an email dataset naturally memorized by Llama-3-8B and GPT-J-6B, and a synthetic social security number dataset that we tune the models to memorize. Compared to other methods, REVS demonstrates superior performance in unlearning sensitive information and robustness to extraction attacks, while retaining underlying model integrity.
Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these mechanisms for Large Language Models (LLMs), revealing insights on how information is stored in a model's parameters and how information flows to and from these parameters in response to specific prompts. However, these studies have not yet been extended to Multi-modal Large Language Models (MLLMs). Given their expanding capabilities and real-world use, we start by studying one aspect of these models -- how MLLMs process information in a factual visual question answering task. We use a constraint-based formulation which views a visual question as having a set of visual or textual constraints that the model's generated answer must satisfy to be correct (e.g. What movie directed by the director in this photo has won a Golden Globe?). Under this setting, we contribute i) a method that extends causal information tracing from pure language to the multi-modal setting, and ii) VQA-Constraints, a test-bed of 9.7K visual questions annotated with constraints. We use these tools to study two open-source MLLMs, LLaVa and multi-modal Phi-2. Our key findings show that these MLLMs rely on MLP and self-attention blocks in much earlier layers for information storage, compared to LLMs whose mid-layer MLPs are more important. We also show that a consistent small subset of visual tokens output by the vision encoder are responsible for transferring information from the image to these causal blocks. We validate these mechanisms by introducing MultEdit, a model-editing algorithm that can correct errors and insert new long-tailed information into MLLMs by targeting these causal blocks.
Recently, while large language models (LLMs) have demonstrated impressive results, they still suffer from hallucination, i.e., the generation of false information. Model editing is the task of fixing factual mistakes in LLMs; yet, most previous works treat it as a one-time task, paying little attention to ever-emerging mistakes generated by LLMs. We address the task of sequential model editing (SME) that aims to rectify mistakes continuously. A Dynamic Auxiliary Fusion Network (DAFNet) is designed to enhance the semantic interaction among the factual knowledge within the entire sequence, preventing catastrophic forgetting during the editing process of multiple knowledge triples. Specifically, (1) for semantic fusion within a relation triple, we aggregate the intra-editing attention flow into auto-regressive self-attention with token-level granularity in LLMs. We further leverage multi-layer diagonal inter-editing attention flow to update the weighted representations of the entire sequence-level granularity. (2) Considering that auxiliary parameters are required to store the knowledge for sequential editing, we construct a new dataset named \textbf{DAFSet}, fulfilling recent, popular, long-tail and robust properties to enhance the generality of sequential editing. Experiments show DAFNet significantly outperforms strong baselines in single-turn and sequential editing. The usage of DAFSet also consistently improves the performance of other auxiliary network-based methods in various scenarios
Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However, these methods either exhibit poor overall performance or struggle to strike a balance between generalization and locality. We propose MEMoE, a model editing adapter utilizing a Mixture of Experts (MoE) architecture with a knowledge anchor routing strategy. MEMoE updates knowledge using a bypass MoE structure, keeping the original parameters unchanged to preserve the general ability of LLMs. And, the knowledge anchor routing ensures that inputs requiring similar knowledge are routed to the same expert, thereby enhancing the generalization of the updated knowledge. Experimental results show the superiority of our approach over both batch editing and sequential batch editing tasks, exhibiting exceptional overall performance alongside outstanding balance between generalization and locality. Our code will be available.
Model editing is an emerging field that focuses on updating the knowledge embedded within large language models (LLMs) without extensive retraining. However, current model editing methods significantly compromise the general abilities of LLMs as the number of edits increases, and this trade-off poses a substantial challenge to the continual learning of LLMs. In this paper, we first theoretically analyze that the factor affecting the general abilities in sequential model editing lies in the condition number of the edited matrix. The condition number of a matrix represents its numerical sensitivity, and therefore can be used to indicate the extent to which the original knowledge associations stored in LLMs are perturbed after editing. Subsequently, statistical findings demonstrate that the value of this factor becomes larger as the number of edits increases, thereby exacerbating the deterioration of general abilities. To this end, a framework termed Perturbation Restraint on Upper bouNd for Editing (PRUNE) is proposed, which applies the condition number restraints in sequential editing. These restraints can lower the upper bound on perturbation to edited models, thus preserving the general abilities. Systematically, we conduct experiments employing three popular editing methods on three LLMs across four representative downstream tasks. Evaluation results show that PRUNE can preserve considerable general abilities while maintaining the editing performance effectively in sequential model editing. The code and data are available at https://github.com/mjy1111/PRUNE.
Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large Scale Knowledge Washing, focusing on unlearning an extensive amount of factual knowledge. Previous unlearning methods usually define the reverse loss and update the model via backpropagation, which may affect the model's fluency and reasoning ability or even destroy the model due to extensive training with the reverse loss. Existing works introduce additional data from downstream tasks to prevent the model from losing capabilities, which requires downstream task awareness. Controlling the tradeoff of unlearning and maintaining existing capabilities is also challenging. To this end, we propose LAW (Large Scale Washing) to update the MLP layers in decoder-only large language models to perform knowledge washing, as inspired by model editing methods and based on the hypothesis that knowledge and reasoning are disentanglable. We derive a new objective with the knowledge to be unlearned to update the weights of certain MLP layers. Experimental results demonstrate the effectiveness of LAW in forgetting target knowledge while maintaining reasoning ability. The code will be open-sourced at https://github.com/wangyu-ustc/LargeScaleWashing.
Recent alignment algorithms such as direct preference optimization (DPO) have been developed to improve the safety of large language models (LLMs) by training these models to match human behaviors exemplified by preference data. However, these methods are both computationally intensive and lacking in controllability and transparency, inhibiting their widespread use. Furthermore, these tuning-based methods require large-scale preference data for training and are susceptible to noisy preference data. In this paper, we introduce a tuning-free alignment alternative, ProFS (Projection Filter for Subspaces), and demonstrate its effectiveness under the use case of toxicity reduction. Grounded on theory from factor analysis, ProFS is a sample-efficient model editing approach that identifies a toxic subspace in the model parameter space and reduces model toxicity by projecting away the detected subspace. The toxic subspace is identified by extracting preference data embeddings from the language model, and removing non-toxic information from these embeddings. We show that ProFS is more sample-efficient than DPO, further showcasing greater robustness to noisy data. Finally, we attempt to connect tuning based alignment with editing, by establishing both theoretical and empirical connections between ProFS and DPO, showing that ProFS can be interpreted as a denoised version of a single DPO step.
Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in memories is a fundamental question for model editing. In this paper, we find that editing either long-term memory (direct model parameters) or working memory (non-parametric knowledge of neural network activations/representations by retrieval) will result in an impossible triangle -- reliability, generalization, and locality can not be realized together in the lifelong editing settings. For long-term memory, directly editing the parameters will cause conflicts with irrelevant pretrained knowledge or previous edits (poor reliability and locality). For working memory, retrieval-based activations can hardly make the model understand the edits and generalize (poor generalization). Therefore, we propose WISE to bridge the gap between memories. In WISE, we design a dual parametric memory scheme, which consists of the main memory for the pretrained knowledge and a side memory for the edited knowledge. We only edit the knowledge in the side memory and train a router to decide which memory to go through when given a query. For continual editing, we devise a knowledge-sharding mechanism where different sets of edits reside in distinct subspaces of parameters, and are subsequently merged into a shared memory without conflicts. Extensive experiments show that WISE can outperform previous model editing methods and overcome the impossible triangle under lifelong model editing of question answering, hallucination, and out-of-distribution settings across trending LLM architectures, e.g., GPT, LLaMA, and Mistral. Code is available at https://github.com/zjunlp/EasyEdit.
Model editing aims to correct outdated or erroneous knowledge in large language models (LLMs) without the need for costly retraining. Lifelong model editing is the most challenging task that caters to the continuous editing requirements of LLMs. Prior works primarily focus on single or batch editing; nevertheless, these methods fall short in lifelong editing scenarios due to catastrophic knowledge forgetting and the degradation of model performance. Although retrieval-based methods alleviate these issues, they are impeded by slow and cumbersome processes of integrating the retrieved knowledge into the model. In this work, we introduce RECIPE, a RetriEval-augmented ContInuous Prompt lEarning method, to boost editing efficacy and inference efficiency in lifelong learning. RECIPE first converts knowledge statements into short and informative continuous prompts, prefixed to the LLM's input query embedding, to efficiently refine the response grounded on the knowledge. It further integrates the Knowledge Sentinel (KS) that acts as an intermediary to calculate a dynamic threshold, determining whether the retrieval repository contains relevant knowledge. Our retriever and prompt encoder are jointly trained to achieve editing properties, i.e., reliability, generality, and locality. In our experiments, RECIPE is assessed extensively across multiple LLMs and editing datasets, where it achieves superior editing performance. RECIPE also demonstrates its capability to maintain the overall performance of LLMs alongside showcasing fast editing and inference speed.
We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascent thesis proposes that facts are recalled from the training corpus through the MLP weights in a manner resembling key-value memory, implying in effect that "knowledge" is stored in the network. Furthermore, by modifying the MLP modules, one can control the language model's generation of factual information. The plausibility of the KN thesis has been demonstrated by the success of KN-inspired model editing methods (Dai et al., 2022; Meng et al., 2022). We find that this thesis is, at best, an oversimplification. Not only have we found that we can edit the expression of certain linguistic phenomena using the same model editing methods but, through a more comprehensive evaluation, we have found that the KN thesis does not adequately explain the process of factual expression. While it is possible to argue that the MLP weights store complex patterns that are interpretable both syntactically and semantically, these patterns do not constitute "knowledge." To gain a more comprehensive understanding of the knowledge representation process, we must look beyond the MLP weights and explore recent models' complex layer structures and attention mechanisms.
Knowledge editing methods (KEs) can update language models' obsolete or inaccurate knowledge learned from pre-training. However, KEs can be used for malicious applications, e.g., inserting misinformation and toxic content. Knowing whether a generated output is based on edited knowledge or first-hand knowledge from pre-training can increase users' trust in generative models and provide more transparency. Driven by this, we propose a novel task: detecting edited knowledge in language models. Given an edited model and a fact retrieved by a prompt from an edited model, the objective is to classify the knowledge as either unedited (based on the pre-training), or edited (based on subsequent editing). We instantiate the task with four KEs, two LLMs, and two datasets. Additionally, we propose using the hidden state representations and the probability distributions as features for the detection. Our results reveal that, using these features as inputs to a simple AdaBoost classifiers establishes a strong baseline. This classifier requires only a limited amount of data and maintains its performance even in cross-domain settings. Last, we find it more challenging to distinguish edited knowledge from unedited but related knowledge, highlighting the need for further research. Our work lays the groundwork for addressing malicious model editing, which is a critical challenge associated with the strong generative capabilities of LLMs.