We call into question the recently popularized method of direct model editing as a means of correcting factual errors in LLM generations. We contrast model editing with three similar but distinct approaches that pursue better defined objectives: (1) retrieval-based architectures, which decouple factual memory from inference and linguistic capabilities embodied in LLMs; (2) concept erasure methods, which aim at preventing systemic bias in generated text; and (3) attribution methods, which aim at grounding generations into identified textual sources. We argue that direct model editing cannot be trusted as a systematic remedy for the disadvantages inherent to LLMs, and while it has proven potential in improving model explainability, it opens risks by reinforcing the notion that models can be trusted for factuality. We call for cautious promotion and application of model editing as part of the LLM deployment process, and for responsibly limiting the use cases of LLMs to those not relying on editing as a critical component.
Recent studies have demonstrated that large language models (LLMs) store massive factual knowledge within their parameters. But existing LLMs are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing interest in the concept of model editing. Despite the emergence of benchmarks and approaches, these unidirectional editing and evaluation have failed to explore the reversal curse. Intuitively, if "The capital of France is" is edited to be a counterfact "London" within a model, then it should be able to naturally reason and recall the reverse fact, i.e., "London is the capital of" followed by "France" instead of "England". In this paper, we study bidirectional language model editing, aiming to provide rigorous model editing evaluation to assess if edited LLMs can recall the editing knowledge bidirectionally. A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing. We surprisingly observe that while current editing methods and LLMs can effectively recall editing facts in the direction of editing, they suffer serious deficiencies when evaluated in the reverse direction. To mitigate the reversal curse, a method named Bidirectionally Inversible Relationship moDeling (BIRD) is proposed. A set of editing objectives that incorporate bidirectional relationships between subject and object into the updated model weights are designed. Experiments show that BIRD improves the performance of four representative LLMs of different sizes via question answering and judgement.
Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' predictions and controlling model behaviors have remained open challenges. We present a framework for interpreting vision transformer's latent tokens with natural language. Given a latent token, our framework retains its semantic information to the final layer using transformer's local operations and retrieves the closest text for explanation. Our approach enables understanding of model visual reasoning procedure without needing additional model training or data collection. Based on the obtained interpretations, our framework allows for model editing that controls model reasoning behaviors and improves model robustness against biases and spurious correlations.
Multilingual large-scale Pretrained Language Models (PLMs) have been shown to store considerable amounts of factual knowledge, but large variations are observed across languages. With the ultimate goal of ensuring that users with different language backgrounds obtain consistent feedback from the same model, we study the cross-lingual consistency (CLC) of factual knowledge in various multilingual PLMs. To this end, we propose a Ranking-based Consistency (RankC) metric to evaluate knowledge consistency across languages independently from accuracy. Using this metric, we conduct an in-depth analysis of the determining factors for CLC, both at model level and at language-pair level. Among other results, we find that increasing model size leads to higher factual probing accuracy in most languages, but does not improve cross-lingual consistency. Finally, we conduct a case study on CLC when new factual associations are inserted in the PLMs via model editing. Results on a small sample of facts inserted in English reveal a clear pattern whereby the new piece of knowledge transfers only to languages with which English has a high RankC score.
Foundation models (FM) have demonstrated remarkable performance across a wide range of tasks (especially in the fields of natural language processing and computer vision), primarily attributed to their ability to comprehend instructions and access extensive, high-quality data. This not only showcases their current effectiveness but also sets a promising trajectory towards the development of artificial general intelligence. Unfortunately, due to multiple constraints, the raw data of the model used for large model training are often inaccessible, so the use of end-to-end models for downstream tasks has become a new research trend, which we call Learn From Model (LFM) in this article. LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks. The study of LFM techniques can be broadly categorized into five major areas: model tuning, model distillation, model reuse, meta learning and model editing. Each category encompasses a repertoire of methods and strategies that aim to enhance the capabilities and performance of FM. This paper gives a comprehensive review of the current methods based on FM from the perspective of LFM, in order to help readers better understand the current research status and ideas. To conclude, we summarize the survey by highlighting several critical areas for future exploration and addressing open issues that require further attention from the research community. The relevant papers we investigated in this article can be accessed at <https://github.com/ruthless-man/Awesome-Learn-from-Model>.
In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the editing process. To facilitate research in this area, we construct a new benchmark, dubbed MMEdit, for editing multimodal LLMs and establishing a suite of innovative metrics for evaluation. We conduct comprehensive experiments involving various model editing baselines and analyze the impact of editing different components for multimodal LLMs. Empirically, we notice that previous baselines can implement editing multimodal LLMs to some extent, but the effect is still barely satisfactory, indicating the potential difficulty of this task. We hope that our work can provide the NLP community with insights. Code and dataset are available in https://github.com/zjunlp/EasyEdit.
This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits. Specifically, we construct PersonalityEdit, a new benchmark dataset to address this task. Drawing on the theory in Social Psychology, we isolate three representative traits, namely Neuroticism, Extraversion, and Agreeableness, as the foundation for our benchmark. We then gather data using GPT-4, generating responses that align with a specified topic and embody the targeted personality trait. We conduct comprehensive experiments involving various baselines and discuss the representation of personality behavior in LLMs. Our findings uncover potential challenges of the proposed task, illustrating several remaining issues. We anticipate that our work can stimulate further annotation in model editing and personality-related research. Code is available at https://github.com/zjunlp/EasyEdit.
Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They can also output toxic or harmful text. To mitigate these safety and informational issues, we propose an attack-and-defense framework for studying the task of deleting sensitive information directly from model weights. We study direct edits to model weights because (1) this approach should guarantee that particular deleted information is never extracted by future prompt attacks, and (2) it should protect against whitebox attacks, which is necessary for making claims about safety/privacy in a setting where publicly available model weights could be used to elicit sensitive information. Our threat model assumes that an attack succeeds if the answer to a sensitive question is located among a set of B generated candidates, based on scenarios where the information would be insecure if the answer is among B candidates. Experimentally, we show that even state-of-the-art model editing methods such as ROME struggle to truly delete factual information from models like GPT-J, as our whitebox and blackbox attacks can recover "deleted" information from an edited model 38% of the time. These attacks leverage two key observations: (1) that traces of deleted information can be found in intermediate model hidden states, and (2) that applying an editing method for one question may not delete information across rephrased versions of the question. Finally, we provide new defense methods that protect against some extraction attacks, but we do not find a single universally effective defense method. Our results suggest that truly deleting sensitive information is a tractable but difficult problem, since even relatively low attack success rates have potentially severe societal implications for real-world deployment of language models.
Large Language Models (LLMs), although powerful in general domains, often perform poorly on domain-specific tasks such as medical question answering (QA). In addition, LLMs tend to function as "black-boxes", making it challenging to modify their behavior. To address the problem, our work employs a transparent process of retrieval augmented generation (RAG), aiming to improve LLM responses without the need for fine-tuning or retraining. Specifically, we propose a comprehensive retrieval strategy to extract medical facts from an external knowledge base, and then inject them into the LLM's query prompt. Focusing on medical QA, we evaluate the impact of different retrieval models and the number of facts on LLM performance using the MedQA-SMILE dataset. Notably, our retrieval-augmented Vicuna-7B model exhibited an accuracy improvement from 44.46% to 48.54%. This work underscores the potential of RAG to enhance LLM performance, offering a practical approach to mitigate the challenges posed by black-box LLMs.
One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise, human-understandable explanations for what neural networks are doing internally. One hypothesised cause of polysemanticity is \textit{superposition}, where neural networks represent more features than they have neurons by assigning features to an overcomplete set of directions in activation space, rather than to individual neurons. Here, we attempt to identify those directions, using sparse autoencoders to reconstruct the internal activations of a language model. These autoencoders learn sets of sparsely activating features that are more interpretable and monosemantic than directions identified by alternative approaches, where interpretability is measured by automated methods. Moreover, we show that with our learned set of features, we can pinpoint the features that are causally responsible for counterfactual behaviour on the indirect object identification task \citep{wang2022interpretability} to a finer degree than previous decompositions. This work indicates that it is possible to resolve superposition in language models using a scalable, unsupervised method. Our method may serve as a foundation for future mechanistic interpretability work, which we hope will enable greater model transparency and steerability.
Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of key-value memories of the Feed-Forward Network (FFN). They usually optimize the TL hidden states to memorize target knowledge and use it to update the weights of the FFN in LLMs. However, the information flow of TL hidden states comes from three parts: Multi-Head Self-Attention (MHSA), FFN, and residual connections. Existing methods neglect the fact that the TL hidden states contains information not specifically required for FFN. Consequently, the performance of model editing decreases. To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns. This implies that MHSA weights do not require updating when new knowledge is introduced. Based on above findings, we introduce PMET, which simultaneously optimizes Transformer Component (TC, namely MHSA and FFN) hidden states, while only using the optimized TC hidden states of FFN to precisely update FFN weights. Our experiments demonstrate that PMET exhibits state-of-the-art performance on both the COUNTERFACT and zsRE datasets. Our ablation experiments substantiate the effectiveness of our enhancements, further reinforcing the finding that the MHSA encodes certain general knowledge extraction patterns and indicating its storage of a small amount of factual knowledge. Our code is available at https://github.com/xpq-tech/PMET.
Modern language models capture a large body of factual knowledge. However, some facts can be incorrectly induced or become obsolete over time, resulting in factually incorrect generations. This has led to the development of various editing methods that allow updating facts encoded by the model. Evaluation of these methods has primarily focused on testing whether an individual fact has been successfully injected, and if similar predictions for other subjects have not changed. Here we argue that such evaluation is limited, since injecting one fact (e.g. ``Jack Depp is the son of Johnny Depp'') introduces a ``ripple effect'' in the form of additional facts that the model needs to update (e.g.``Jack Depp is the sibling of Lily-Rose Depp''). To address this issue, we propose a novel set of evaluation criteria that consider the implications of an edit on related facts. Using these criteria, we then construct RippleEdits, a diagnostic benchmark of 5K factual edits, capturing a variety of types of ripple effects. We evaluate prominent editing methods on RippleEdits, showing that current methods fail to introduce consistent changes in the model's knowledge. In addition, we find that a simple in-context editing baseline obtains the best scores on our benchmark, suggesting a promising research direction for model editing.
The Right to be Forgotten (RTBF) was first established as the result of the ruling of Google Spain SL, Google Inc. v AEPD, Mario Costeja Gonz\'alez, and was later included as the Right to Erasure under the General Data Protection Regulation (GDPR) of European Union to allow individuals the right to request personal data be deleted by organizations. Specifically for search engines, individuals can send requests to organizations to exclude their information from the query results. It was a significant emergent right as the result of the evolution of technology. With the recent development of Large Language Models (LLMs) and their use in chatbots, LLM-enabled software systems have become popular. But they are not excluded from the RTBF. Compared with the indexing approach used by search engines, LLMs store, and process information in a completely different way. This poses new challenges for compliance with the RTBF. In this paper, we explore these challenges and provide our insights on how to implement technical solutions for the RTBF, including the use of differential privacy, machine unlearning, model editing, and guardrails. With the rapid advancement of AI and the increasing need of regulating this powerful technology, learning from the case of RTBF can provide valuable lessons for technical practitioners, legal experts, organizations, and authorities.
Recent model editing techniques promise to mitigate the problem of memorizing false or outdated associations during LLM training. However, we show that these techniques can introduce large unwanted side effects which are not detected by existing specificity benchmarks. We extend the existing CounterFact benchmark to include a dynamic component and dub our benchmark CounterFact+. Additionally, we extend the metrics used for measuring specificity by a principled KL divergence-based metric. We use this improved benchmark to evaluate recent model editing techniques and find that they suffer from low specificity. Our findings highlight the need for improved specificity benchmarks that identify and prevent unwanted side effects.
Despite Graph Neural Networks (GNNs) have achieved prominent success in many graph-based learning problem, such as credit risk assessment in financial networks and fake news detection in social networks. However, the trained GNNs still make errors and these errors may cause serious negative impact on society. \textit{Model editing}, which corrects the model behavior on wrongly predicted target samples while leaving model predictions unchanged on unrelated samples, has garnered significant interest in the fields of computer vision and natural language processing. However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs' widespread applicability. To fill the gap, we first observe that existing model editing methods significantly deteriorate prediction accuracy (up to $50\%$ accuracy drop) in GNNs while a slight accuracy drop in multi-layer perception (MLP). The rationale behind this observation is that the node aggregation in GNNs will spread the editing effect throughout the whole graph. This propagation pushes the node representation far from its original one. Motivated by this observation, we propose \underline{E}ditable \underline{G}raph \underline{N}eural \underline{N}etworks (EGNN), a neighbor propagation-free approach to correct the model prediction on misclassified nodes. Specifically, EGNN simply stitches an MLP to the underlying GNNs, where the weights of GNNs are frozen during model editing. In this way, EGNN disables the propagation during editing while still utilizing the neighbor propagation scheme for node prediction to obtain satisfactory results. Experiments demonstrate that EGNN outperforms existing baselines in terms of effectiveness (correcting wrong predictions with lower accuracy drop), generalizability (correcting wrong predictions for other similar nodes), and efficiency (low training time and memory) on various graph datasets.
Editing model parameters directly in Transformers makes updating open-source transformer-based models possible without re-training (Meng et al., 2023). However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer. Commonsense knowledge with multiple correct answers, e.g., an apple can be green or red but not transparent, has not been studied but is as essential for enhancing transformers' reliability and usefulness. In this paper, we investigate whether commonsense judgments are causally associated with localized, editable parameters in Transformers, and we provide an affirmative answer. We find that directly applying the MEMIT editing algorithm results in sub-par performance and improve it for the commonsense domain by varying edit tokens and improving the layer selection strategy, i.e., $MEMIT_{CSK}$. GPT-2 Large and XL models edited using $MEMIT_{CSK}$ outperform best-fine-tuned baselines by 10.97% and 10.73% F1 scores on PEP3k and 20Q datasets. In addition, we propose a novel evaluation dataset, PROBE SET, that contains unaffected and affected neighborhoods, affected paraphrases, and affected reasoning challenges. $MEMIT_{CSK}$ performs well across the metrics while fine-tuning baselines show significant trade-offs between unaffected and affected metrics. These results suggest a compelling future direction for incorporating feedback about common sense into Transformers through direct model editing.
Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To this end, the past few years have witnessed a surge in techniques for editing LLMs, the objective of which is to efficiently alter the behavior of LLMs within a specific domain without negatively impacting performance across other inputs. This paper embarks on a deep exploration of the problems, methods, and opportunities related to model editing for LLMs. In particular, we provide an exhaustive overview of the task definition and challenges associated with model editing, along with an in-depth empirical analysis of the most progressive methods currently at our disposal. We also build a new benchmark dataset to facilitate a more robust evaluation and pinpoint enduring issues intrinsic to existing techniques. Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context. Code and datasets are available at https://github.com/zjunlp/EasyEdit.
Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present in the training data. Thus, there is a need to control these assumptions without requiring explicit user input or costly re-training. In this work, we aim to edit a given implicit assumption in a pre-trained diffusion model. Our Text-to-Image Model Editing method, TIME for short, receives a pair of inputs: a "source" under-specified prompt for which the model makes an implicit assumption (e.g., "a pack of roses"), and a "destination" prompt that describes the same setting, but with a specified desired attribute (e.g., "a pack of blue roses"). TIME then updates the model's cross-attention layers, as these layers assign visual meaning to textual tokens. We edit the projection matrices in these layers such that the source prompt is projected close to the destination prompt. Our method is highly efficient, as it modifies a mere 2.2% of the model's parameters in under one second. To evaluate model editing approaches, we introduce TIMED (TIME Dataset), containing 147 source and destination prompt pairs from various domains. Our experiments (using Stable Diffusion) show that TIME is successful in model editing, generalizes well for related prompts unseen during editing, and imposes minimal effect on unrelated generations.
The current trend toward ever-larger models makes standard retraining procedures an ever-more expensive burden. For this reason, there is growing interest in model editing, which enables computationally inexpensive, interpretable, post-hoc model modifications. While many model editing techniques are promising, research on the properties of edited models is largely limited to evaluation of validation accuracy. The robustness of edited models is an important and yet mostly unexplored topic. In this paper, we employ recently developed techniques from the field of deep learning robustness to investigate both how model editing affects the general robustness of a model, as well as the robustness of the specific behavior targeted by the edit. We find that edits tend to reduce general robustness, but that the degree of degradation depends on the editing algorithm and layers chosen. Motivated by these observations we introduce a new model editing algorithm, 1-layer interpolation (1-LI), which uses weight-space interpolation to navigate the trade-off between editing task accuracy and general robustness.
3D model reconstruction from a single image has achieved great progress with the recent deep generative models. However, the conventional reconstruction approaches with template mesh deformation and implicit fields have difficulty in reconstructing non-watertight 3D mesh models, such as garments. In contrast to image-based modeling, the sketch-based approach can help users generate 3D models to meet the design intentions from hand-drawn sketches. In this study, we propose Sketch2Cloth, a sketch-based 3D garment generation system using the unsigned distance fields from the user's sketch input. Sketch2Cloth first estimates the unsigned distance function of the target 3D model from the sketch input, and extracts the mesh from the estimated field with Marching Cubes. We also provide the model editing function to modify the generated mesh. We verified the proposed Sketch2Cloth with quantitative evaluations on garment generation and editing with a state-of-the-art approach.