Related papers: Mistral-SPLADE: LLMs for better Learned Sparse Ret…
Retrieval-Augmented Generation (RAG) has emerged as a way to complement the in-context knowledge of Large Language Models (LLMs) by integrating external documents. However, real-world applications demand not only accuracy but also…
The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language. However, their conventional usage through…
Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks by leveraging the fine-grained information that phrases offer. In our work, we propose a new task formulation of dense retrieval, cross-lingual…
This study addresses the application of encoder-only Pre-trained Language Models (PLMs) in keyphrase generation (KPG) amidst the broader availability of domain-tailored encoder-only models compared to encoder-decoder models. We investigate…
Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…
Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…
We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively…
Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify…
Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients,…
In this study, we investigate the integration of a large language model (LLM) with an automatic speech recognition (ASR) system, specifically focusing on enhancing rare word recognition performance. Using a 190,000-hour dataset primarily…
Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks.…
Sparse Representation (SR) of signals or data has a well founded theory with rigorous mathematical error bounds and proofs. SR of a signal is given by superposition of very few columns of a matrix called Dictionary, implicitly reducing…
Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…
Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…
Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data privacy concerns, which make them impractical for many real-world applications. A natural…
Sequential recommender systems (SRS) aim to predict users' subsequent choices based on their historical interactions and have found applications in diverse fields such as e-commerce and social media. However, in real-world systems, most…
Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…
Large language models have become extremely popular recently due to their ability to achieve strong performance on a variety of tasks, such as text generation and rewriting, but their size and computation cost make them difficult to access,…
The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive…