相关论文: KiC: Keyword-inspired Cascade for Cost-Efficient T…

The goal of knowledge graph completion (KGC) is to predict missing facts among entities. Previous methods for KGC re-ranking are mostly built on non-generative language models to obtain the probability of each candidate. Recently,…

Accurate prediction of treatment outcomes in lung cancer remains challenging due to the sparsity, heterogeneity, and contextual overload of real-world electronic health data. Traditional models often fail to capture semantic information…

While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to…

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature…

In the age of information abundance, the ability to provide users with contextually relevant and concise information is crucial. Keyword in Context (KIC) generation is a task that plays a vital role in and generation applications, such as…

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved…

Computer-aided design (CAD) is fundamental to modern engineering and manufacturing, but creating CAD models still requires expert knowledge and specialized software. Recent advances in large language models (LLMs) open up the possibility of…

While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform well on the most challenging tasks in the Bird-Bench (BIRD) benchmark. This is due to…

Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC…

Large language models (LLMs) have been widely used for relevance assessment in information retrieval. However, our study demonstrates that combining two distinct small language models (SLMs) with different architectures can outperform LLMs…

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and…

Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical Compression and…

Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small…

Spurred by recent advances in Large Language Models (LLMs), virtual assistants are poised to take a leap forward in terms of their dialogue capabilities. Yet a major bottleneck to achieving genuinely transformative task-oriented dialogue…

Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning. However, humans typically…

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to…

Generative tasks, such as text generation and question answering, hold a crucial position in the realm of mobile applications. Due to their sensitivity to privacy concerns, there is a growing demand for their execution directly on mobile…

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

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…

Speculative decoding has emerged as a promising lossless approach for accelerating Large Language Models (LLMs). As reasoning LLMs increasingly suffer from decode-stage overhead and approximation-based methods degrade accuracy, lossless…