相关论文: Context-Robust Knowledge Editing for Language Mode…

Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing…

Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent…

We propose a framework to modularize the training of neural language models that use diverse forms of sentence-external context (including metadata) by eliminating the need to jointly train sentence-external and within-sentence encoders.…

Retrieval-Augmented Generation (RAG) systems have recently shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses.…

Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and…

Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effectively integrate cues from multiple modalities. We propose Mixture of Speech-Text…

This preliminary study investigates the usefulness of sentence-level Quality Estimation (QE) in English-Chinese Machine Translation Post-Editing (MTPE), focusing on its impact on post-editing speed and student translators' perceptions. It…

Unified diffusion editors often rely on a fixed, shared backbone for diverse tasks, suffering from task interference and poor adaptation to heterogeneous demands (e.g., local vs global, semantic vs photometric). In particular, prevalent…

Conversational recommender systems (CRS) utilize natural language interactions and dialogue history to infer user preferences and provide accurate recommendations. Due to the limited conversation context and background knowledge, existing…

Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign textual findings with visual evidence, leading to unreliable…

Large language models are increasingly used as coding agents for software engineering tasks. Current benchmarks mainly evaluate whether the agent can correctly solve the request or fix the bugs. They largely treat tasks as independent and…

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and…

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…

In recent years, BERT has made significant breakthroughs on many natural language processing tasks and attracted great attentions. Despite its accuracy gains, the BERT model generally involves a huge number of parameters and needs to be…

This paper details the methodology behind CoPE, a policy-steerable small language model capable of fast and accurate content labeling. We present a novel training curricula called Contradictory Example Training that enables the model to…

Large Language Models (LLM's) have demonstrated considerable success in various Natural Language Processing tasks, but they have yet to attain state-of-the-art performance in Neural Machine Translation (NMT). Nevertheless, their significant…

Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and…

This paper investigates two complementary paradigms for predicting machine translation (MT) quality: source-side difficulty prediction and candidate-side quality estimation (QE). The rapid adoption of Large Language Models (LLMs) into MT…

Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…