相关论文: Multiple Token Divergence: Measuring and Steering …

Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread…

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Task-oriented dialogue (TOD) systems are commonly designed with the presumption that each utterance represents a single intent. However, this assumption may not accurately reflect real-world situations, where users frequently express…

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…

Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the classical decoding algorithm that interprets noisy syndrome measurements. Among all possible…

Masked diffusion language models (MDLMs) have emerged as a promising alternative to dominant autoregressive approaches. Although they achieve competitive performance on several tasks, a substantial gap remains in open-ended text generation.…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

This study investigates the performance of the DeepSeek R1 language model on 30 challenging mathematical problems derived from the MATH dataset, problems that previously proved unsolvable by other models under time constraints. Unlike prior…

Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains, several benchmark tasks can be solved with 100\% success…

Previous stance detection studies typically concentrate on evaluating stances within individual instances, thereby exhibiting limitations in effectively modeling multi-party discussions concerning the same specific topic, as naturally…

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

Tensor decomposition methods are popular tools for analysis of multi-way datasets from social media, healthcare, spatio-temporal domains, and others. Widely adopted models such as Tucker and canonical polyadic decomposition (CPD) follow a…

Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these…

Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers. It can effectively reduce the training…

Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal…

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring…