13 accepted papers
Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach seeks to minimize the conditional negative log-likelihood of the label sequence, typically estimated using the mean squa…
Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on explicit preference data with high collection costs. In this work, we study implicit reward modeling---learning reward models from implicit human feedback--…
Large-scale pre-training has been shown to benefit speech translation tasks. However, existing multimodal pre-training efforts rely on parallel corpora for semantic alignment, potentially limiting performance to the scale of available data and causing data imbalance. Hence, we propose an adversarial…
Generative document retrieval is a novel retrieval framework, which represents documents as identifiers (DocID) and retrieves documents by generating DocIDs. It has the advantage of end-to-end optimization over traditional retrieval methods and has attracted much research interest. Nonetheless, the…
Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural ch…
Significant progress has recently been made in combining Speech Foundation Models (SFMs) and Large Language Models (LLMs) into a unified model to tackle Speech-to-Text Translation (ST) tasks. However, fine-tuning LLMs to adapt to specific downstream tasks requires substantial resources, which is oft…
Precise recognition of search intent in Retrieval-Augmented Generation (RAG) systems remains a challenging goal, especially under resource constraints and for complex queries with nested structures and dependencies. This paper presents **QCompiler**, a neuro-symbolic framework inspired by linguistic…
Retrieval-augmented generation (RAG) has emerged as a pivotal technology in natural language processing, owing to its efficacy in generating factual content. However, its informative inputs and complex paradigms often lead to a greater variety of errors. Consequently, achieving automated on-policy a…
Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of sep…
Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors. To
Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive researc…
Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in natural language processing. Existing methods for GDR and GAR rely on separate retrieval and reader modules, which hinder si…
This paper proposes a novel architecture, Cross Attention Augmented Transducer (CAAT), for simultaneous translation. The framework aims to jointly optimize the policy and translation models. To effectively consider all possible READ-WRITE simultaneous translation action paths, we adapt the online au…