The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous studies, recent research reported a near-random performance in different settings, highlighting a significant performance inconsistency. We assume that a single setting doesn’t represent the distribution of the vast corpora, causing members and non-members with different distributions to be sampled and causing inconsistency. In this study, instead of a single setting, we statistically revisit MIA methods from various settings with thousands of experiments for each MIA method, along with study in text feature, embedding, threshold decision, and decoding dynamics of members and non-members. We found that (1) MIA performance improves with model size and varies with domains, while most methods do not statistically outperform baselines, (2) Though MIA performance is generally low, a notable amount of differentiable member and non-member outliers exists and vary across MIA methods, (3) Deciding a threshold to separate members and non-members is an overlooked challenge, (4) Text dissimilarity and long text benefit MIA performance, (5) Differentiable or not is reflected in the LLM embedding, (6) Member and non-members show different decoding dynamics.

Large Language Models (LLMs) can generate the same sequences contained in the pre-train corpora, known as memorization.Previous research studied it at a macro level, leaving micro yet important questions under-explored, e.g., what makes sentences memorized, the dynamics when generating memorized sequence, its connection to unmemorized sequence, and its predictability.We answer the above questions by analyzing the relationship of memorization with outputs from LLM, namely, embeddings, probability distributions, and generated tokens.A memorization score is calculated as the overlap between generated tokens and actual continuations when the LLM is prompted with a context sequence from the pre-train corpora.Our findings reveal:(1) The inter-correlation between memorized/unmemorized sentences, model size, continuation size, and context size, as well as the transition dynamics between sentences of different memorization scores,(2) A sudden drop and increase in the frequency of input tokens when generating memorized/unmemorized sequences (boundary effect),(3) Cluster of sentences with different memorization scores in the embedding space,(4) An inverse boundary effect in the entropy of probability distributions for generated memorized/unmemorized sequences,(5) The predictability of memorization is related to model size and continuation length. In addition, we show a Transformer model trained by the hidden states of LLM can predict unmemorized tokens.

We study the problem of integrating cognitive language processing signals (e.g., eye-tracking or EEG data) into pre-trained language models like BERT. Existing methods typically fine-tune pre-trained models on cognitive data, ignoring the semantic gap between the texts and cognitive signals. To fill the gap, we propose CogBERT, a framework that can induce fine-grained cognitive features from cognitive data and incorporate cognitive features into BERT by adaptively adjusting the weight of cognitive features for different NLP tasks. Extensive experiments show that: (1) Cognition-guided pre-trained models can consistently perform better than basic pre-trained models on ten NLP tasks. (2) Different cognitive features contribute differently to different NLP tasks. Based on this observation, we give a fine-grained explanation of why cognitive data is helpful for NLP. (3) Different transformer layers of pre-trained models should encode different cognitive features, with word-level cognitive features at the bottom and semantic-level cognitive features at the top. (4) Attention visualization demonstrates that CogBERT aligns with human gaze patterns and improves its natural language comprehension ability.

This paper proposes a data representation framework for semantic parsing and task-oriented dialogue systems, aiming to achieve a uniform representation for syntactically and semantically diverse machine-readable formats.Current NLP systems heavily rely on adapting pre-trained language models to specific tasks, and this approach has been proven effective for modeling natural language texts.However, little attention has been paid to the representation of machine-readable formats, such as database queries and dialogue states.We present a method for converting original machine-readable formats of semantic parsing and task-oriented dialogue datasets into a syntactically and semantically uniform representation.We define a meta grammar for syntactically uniform representations and translate semantically equivalent functions into a uniform vocabulary.Empirical experiments on 13 datasets show that accuracy consistently improves over original formats, revealing the advantage of the proposed representation.Additionally, we show that the proposed representation allows for transfer learning across datasets.