相关论文: Grounded Token Initialization for New Vocabulary i…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

The escalating computational costs of Large Language Model (LLM) inference have become a critical barrier to their widespread and sustainable deployment. While existing optimization strategies are effective, they are predominantly based on…

Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks. While many natural language understanding challenges can…

While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We…

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…

Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate…

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any…

Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine an information-free, fully masked initialization into…

Search and recommendation (S&R) are core to online platforms, addressing explicit intent through queries and modeling implicit intent from behaviors, respectively. Their complementary roles motivate a unified modeling paradigm. Early…

Pre-trained language models (PTLMs) acquire domain-independent linguistic knowledge through pre-training with massive textual resources. Additional pre-training is effective in adapting PTLMs to domains that are not well covered by the…

Grammars provide a convenient and powerful mechanism to define the space of possible solutions for a range of problems. However, when used in grammatical evolution (GE), great care must be taken in the design of a grammar to ensure that the…

Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently…

Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning…

By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…

A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary. This potentially weakens the effect when applying pretrained models into natural language generation (NLG) tasks,…

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…

Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many applications, e.g., retrieval augmented generation (RAG),…

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities…

Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is…

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…