Existing example-based prediction explanation methods often bridge test and training data points through the model's parameters or latent representations. While these methods offer clues to the causes of model predictions, they often exhibit innate shortcomings, such as incurring significant computational overhead or producing coarse-grained explanations. This paper presents a Highly-precise and Data-centric Explanation (HD-Explain), a straightforward prediction explanation method exploiting properties of Kernelized Stein Discrepancy (KSD). Specifically, the KSD uniquely defines a parameterized kernel function for a trained model that encodes model-dependent data correlation. By leveraging the kernel function, one can identify training samples that provide the best predictive support to a test point efficiently. We conducted thorough analyses and experiments across multiple classification domains, where we show that HD-Explain outperforms existing methods from various aspects, including 1) preciseness (fine-grained explanation), 2) consistency, and 3) computation efficiency, leading to a surprisingly simple, effective, and robust prediction explanation solution.
Approaches to aligning large language models (LLMs) with human values has focused on correcting misalignment that emerges from pretraining. However, this focus overlooks another source of misalignment: bad actors might purposely fine-tune LLMs to achieve harmful goals. In this paper, we present an emerging threat model that has arisen from alignment circumvention and fine-tuning attacks. However, lacking in previous works is a clear presentation of the conditions for effective defence. We propose a set of conditions for effective defence against harmful fine-tuning in LLMs called "Immunization conditions," which help us understand how we would construct and measure future defences. Using this formal framework for defence, we offer a synthesis of different research directions that might be persued to prevent harmful fine-tuning attacks and provide a demonstration of how to use these conditions experimentally showing early results of using an adversarial loss to immunize LLama2-7b-chat.
Evaluations of model editing currently only use the `next few token' completions after a prompt. As a result, the impact of these methods on longer natural language generation is largely unknown. We introduce long-form evaluation of model editing (\textbf{\textit{LEME}}) a novel evaluation protocol that measures the efficacy and impact of model editing in long-form generative settings. Our protocol consists of a machine-rated survey and a classifier which correlates well with human ratings. Importantly, we find that our protocol has very little relationship with previous short-form metrics (despite being designed to extend efficacy, generalization, locality, and portability into a long-form setting), indicating that our method introduces a novel set of dimensions for understanding model editing methods. Using this protocol, we benchmark a number of model editing techniques and present several findings including that, while some methods (ROME and MEMIT) perform well in making consistent edits within a limited scope, they suffer much more from factual drift than other methods. Finally, we present a qualitative analysis that illustrates common failure modes in long-form generative settings including internal consistency, lexical cohesion, and locality issues.
We introduce SPUD (Semantically Perturbed Universal Dependencies), a framework for creating nonce treebanks for the multilingual Universal Dependencies (UD) corpora. SPUD data satisfies syntactic argument structure, provides syntactic annotations, and ensures grammaticality via language-specific rules. We create nonce data in Arabic, English, French, German, and Russian, and demonstrate two use cases of SPUD treebanks. First, we investigate the effect of nonce data on word co-occurrence statistics, as measured by perplexity scores of autoregressive (ALM) and masked language models (MLM). We find that ALM scores are significantly more affected by nonce data than MLM scores. Second, we show how nonce data affects the performance of syntactic dependency probes. We replicate the findings of M\"uller-Eberstein et al. (2022) on nonce test data and show that the performance declines on both MLMs and ALMs wrt. original test data. However, a majority of the performance is kept, suggesting that the probe indeed learns syntax independently from semantics.
Neuron analysis provides insights into how knowledge is structured in representations and discovers the role of neurons in the network. In addition to developing an understanding of our models, neuron analysis enables various applications such as debiasing, domain adaptation and architectural search. We present NeuroX, a comprehensive open-source toolkit to conduct neuron analysis of natural language processing models. It implements various interpretation methods under a unified API, and provides a framework for data processing and evaluation, thus making it easier for researchers and practitioners to perform neuron analysis. The Python toolkit is available at https://www.github.com/fdalvi/NeuroX. Demo Video available at https://youtu.be/mLhs2YMx4u8.
The proliferation of deep neural networks in various domains has seen an increased need for the interpretability of these models, especially in scenarios where fairness and trust are as important as model performance. A lot of independent work is being carried out to: i) analyze what linguistic and non-linguistic knowledge is learned within these models, and ii) highlight the salient parts of the input. We present NxPlain, a web application that provides an explanation of a model's prediction using latent concepts. NxPlain discovers latent concepts learned in a deep NLP model, provides an interpretation of the knowledge learned in the model, and explains its predictions based on the used concepts. The application allows users to browse through the latent concepts in an intuitive order, letting them efficiently scan through the most salient concepts with a global corpus level view and a local sentence-level view. Our tool is useful for debugging, unraveling model bias, and for highlighting spurious correlations in a model. A hosted demo is available here: https://nxplain.qcri.org.
Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of evaluation benchmark and metrics have led to siloed progress within these various methods, with very little work comparing them and highlighting their strengths and weaknesses. The reason for this discrepancy is the difficulty of creating ground truth datasets, for example, many neurons within a given model may learn the same phenomena, and hence there may not be one correct answer. Moreover, a learned phenomenon may spread across several neurons that work together -- surfacing these to create a gold standard challenging. In this work, we propose an evaluation framework that measures the compatibility of a neuron analysis method with other methods. We hypothesize that the more compatible a method is with the majority of the methods, the more confident one can be about its performance. We systematically evaluate our proposed framework and present a comparative analysis of a large set of neuron interpretation methods. We make the evaluation framework available to the community. It enables the evaluation of any new method using 20 concepts and across three pre-trained models.The code is released at https://github.com/fdalvi/neuron-comparative-analysis
The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in pre-trained Language Models (pLMs). We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts. To facilitate the process, we provide auto-annotations of the concepts (based on traditional linguistic ontologies). Such annotations enable development of a linguistic resource that directly represents latent concepts learned within deep NLP models. These include not just traditional linguistic concepts, but also task-specific or sensitive concepts (words grouped based on gender or religious connotation) that helps the annotators to mark bias in the model. The framework consists of two parts (i) concept discovery and (ii) annotation platform.
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a trade-off. The goal of this work is to provide an in depth comparison of different approaches for adversarial training in language models. Specifically, we study the effect of pre-training data augmentation as well as training time input perturbations vs. embedding space perturbations on the robustness and generalization of BERT-like language models. Our findings suggest that better robustness can be achieved by pre-training data augmentation or by training with input space perturbation. However, training with embedding space perturbation significantly improves generalization. A linguistic correlation analysis of neurons of the learned models reveal that the improved generalization is due to `more specialized' neurons. To the best of our knowledge, this is the first work to carry out a deep qualitative analysis of different methods of generating adversarial examples in adversarial training of language models.
We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the representational space using hierarchical clustering. We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its fine-tuned version. We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information. We perform a thorough analysis, comparing pre-trained and fine-tuned models across three models and three downstream tasks. The notable findings of our work are: i) the latent space of the higher layers evolve towards task-specific concepts, ii) whereas the lower layers retain generic concepts acquired in the pre-trained model, iii) we discovered that some concepts in the higher layers acquire polarity towards the output class, and iv) that these concepts can be used for generating adversarial triggers.