Related papers: Transformers Remember First, Forget Last: Dual-Pro…

Recent advances in Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities. While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit…

Evaluating LLM forecasting capabilities is constrained by a fundamental tension: prospective evaluation offers methodological rigor but prohibitive latency, while retrospective forecasting (RF) -- evaluating on already-resolved events --…

Generative Large Language Models (LLMs) have shown promising results in text annotation using zero-shot and few-shot learning. Yet these approaches do not allow the model to retain information from previous annotations, making each response…

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…

Structured state-space models (SSMs) have been developed to offer more persistent memory retention than traditional recurrent neural networks, while maintaining real-time inference capabilities and addressing the time-complexity limitations…

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI),…

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

Memorization, or the tendency of large language models (LLMs) to output entire sequences from their training data verbatim, is a key concern for safely deploying language models. In particular, it is vital to minimize a model's memorization…

Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

Modern NLP models are becoming better conversational agents than their predecessors. Recurrent Neural Networks (RNNs) and especially Long-Short Term Memory (LSTM) features allow the agent to better store and use information about semantic…

Large language models (LLMs) are increasingly deployed in information systems, including being used as second-stage rerankers in information retrieval pipelines, yet their susceptibility to recency bias has received little attention. We…

The pervasiveness of proprietary language models has raised critical privacy concerns, necessitating advancements in private inference (PI), where computations are performed directly on encrypted data without revealing users' sensitive…

Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL…

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

Much of what we remember is not due to intentional selection, but simply a by-product of perceiving. This raises a foundational question about the architecture of the mind: How does perception interface with and influence memory? Here,…

Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…