Related papers: FORGE: Fragment-Oriented Ranking and Generation fo…

The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and which are wrong. In this paper, propose a method to effectively…

In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. Specifically, previous studies have reported multiple modeling biases that the…

Cross-lingual Machine Reading Comprehension (xMRC) is challenging due to the lack of training data in low-resource languages. The recent approaches use training data only in a resource-rich language like English to fine-tune large-scale…

This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty. Traditional methods often fail to leverage contextual…

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher…

Retrieval-Augmented Generation (RAG) systems lose retrieval accuracy when similar documents coexist in the vector database, causing unnecessary information, hallucinations, and factual errors. To alleviate this issue, we propose CHOP, a…

Feature engineering has become one of the most important steps to improve model prediction performance, and to produce quality datasets. However, this process requires non-trivial domain-knowledge which involves a time-consuming process.…

State-of-the-art language models can exhibit impressive reasoning refinement capabilities on math, science or coding tasks. However, recent work demonstrates that even the best models struggle to identify \textit{when and where to refine}…

While Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external knowledge, they still face persistent challenges in retrieval inefficiency and the inability of LLMs to filter out irrelevant…

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing…

We study contextual stochastic optimization problems, where we leverage rich auxiliary observations (e.g., product characteristics) to improve decision making with uncertain variables (e.g., demand). We show how to train forest decision…

Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often struggle to filter out irrelevant documents within the…

Fragment-Based Drug Discovery (FBDD) is a popular approach in early drug development, but designing effective linkers to combine disconnected molecular fragments into chemically and pharmacologically viable candidates remains challenging.…

LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we identify a persistent failure mode in current propose-then-select pipelines. Although…

Accurate semantic labeling of image pixels is difficult because intra-class variability is often greater than inter-class variability. In turn, fast semantic segmentation is hard because accurate models are usually too complicated to also…

Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate distorted or low-quality images, especially in certain classes.…

Traditional Retrieval-Augmented Generation (RAG) struggles with complex queries that lack strong signals to retrieve the most relevant context, forcing a trade-off between choosing a small context that misses key information and a large…

Semantic parsing is the process of translating natural language utterances into logical forms, which has many important applications such as question answering and instruction following. Sequence-to-sequence models have been very successful…

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…