Related papers: CARGO: A Framework for Confidence-Aware Routing of…
Retrieval-Augmented Generation pipelines span a wide range of retrieval strategies that differ substantially in token cost and capability. Selecting the right strategy per query is a practical efficiency problem, yet no routing classifiers…
To balance the quality and inference cost of a Foundation Model (FM, such as large language models (LLMs)) powered software, people often opt to train a routing model that routes requests to FMs with different sizes and capabilities.…
Reasoning language models have demonstrated remarkable performance on many challenging tasks in math, science, and coding. Choosing the right reasoning model for practical deployment involves a performance and cost tradeoff at two key…
Large language models (LLMs) are reshaping the recommender system paradigm by enabling users to express preferences and receive recommendations through conversations. Yet, aligning LLMs to the recommendation task remains challenging:…
The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external…
Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…
While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…
Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference…
Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text…
Researchers and practitioners operating on a limited budget face the cost-performance trade-off dilemma. The challenging decision often centers on whether to use a large LLM with better performance or a smaller one with reduced costs. This…
Recent studies have demonstrated the effectiveness of using large language language models (LLMs) in passage ranking. The listwise approaches, such as RankGPT, have become new state-of-the-art in this task. However, the efficiency of…
Large Language Models (LLMs) have revolutionized natural language processing, but their varying capabilities and costs pose challenges in practical applications. LLM routing addresses this by dynamically selecting the most suitable LLM for…
While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO) -- searching high-dimensional solution spaces under hard constraints -- remains…
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…
Large language models (LLMs) are widely applied in chatbots, code generators, and search engines. Workload such as chain-of-throught, complex reasoning, agent services significantly increase the inference cost by invoke the model…
Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across generations. We propose Base-Aligned Model Collaboration (BACo), an inference-time token-level…
Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods such as LangBridge and MindMerger raise accuracy on mid and high-resource…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer user queries. The effectiveness of RAG depends…
Large language models (LLMs) commonly struggle with specialized or emerging topics which are rarely seen in the training corpus. Graph-based retrieval-augmented generation (GraphRAG) addresses this by structuring domain knowledge as a graph…
The emergence of large language models (LLMs), pre-trained on massive datasets, has demonstrated strong performance across a wide range of natural language processing (NLP) tasks, including text classification. While prior studies have…