Related papers: An Ensemble Approach to Personalized Real Time Pre…

Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those entities. We propose a general method to…

Information-seeking conversation, which aims to help users gather information through conversation, has achieved great progress in recent years. However, the research is still stymied by the scarcity of training data. To alleviate this…

Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition…

Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

This study investigates an explainable reasoning method for financial decision-making based on knowledge-enhanced large language model agents. To address the limitations of traditional financial decision methods that rely on parameterized…

Enhancing word usage is a desired feature for writing assistance. To further advance research in this area, this paper introduces "Smart Word Suggestions" (SWS) task and benchmark. Unlike other works, SWS emphasizes end-to-end evaluation…

Real-world recommendation systems commonly offer diverse content scenarios for users to interact with. Considering the enormous number of users in industrial platforms, it is infeasible to utilize a single unified recommendation model to…

Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have…

Continual fine-tuning of large language models (LLMs) suffers from catastrophic forgetting. Rehearsal-based methods mitigate this problem by retaining a small set of old data. Nevertheless, they still suffer inevitable performance loss.…

Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and…

Large language models have demonstrated exceptional capabilities in tasks involving natural language generation, reasoning, and comprehension. This study aims to construct prompts and comments grounded in the diverse scoring criteria…

Due to flourish of the Web 2.0, web opinion sources are rapidly emerging containing precious information useful for both customers and manufactures. Recently, feature based opinion mining techniques are gaining momentum in which customer…

Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve…

Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain suboptimal in multi-turn interactions, often relying on incorrect…

We propose a text editor to help users plan, structure and reflect on their writing process. It provides continuously updated paragraph-wise summaries as margin annotations, using automatic text summarization. Summary levels range from full…