Related papers: PDR: A Plug-and-Play Positional Decay Framework fo…
Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best…
Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…
Large Vision-Language Models (LVLMs) incur substantial inference costs due to the processing of a vast number of visual tokens. Existing methods typically struggle to model progressive visual token reduction as a multi-step decision process…
Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genuine reasoning ability. We introduce chess as a controlled testbed aimed at disentangling these…
Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…
Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-answering systems. However, they require large amounts of…
The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…
Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs. Prevailing unlearning methods generally rely on gradient ascent and its variants to lower the…
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…
The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcement learning, while LLMs have been extensively used in…
Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…
Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically…
Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…
Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…
Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…
Students have a limited time to study and are typically ineffective at allocating study time. Machine-directed study strategies that identify which items need reinforcement and dictate the spacing of repetition have been shown to help…
Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…
Recent advancements in large language models (LLMs) have demonstrated that progressive refinement, rather than providing a single answer, results in more accurate and thoughtful outputs. However, existing methods often rely heavily on…