Related papers: IEKM: A Model Incorporating External Keyword Matri…

Pairwise preferences over model responses are widely collected to evaluate and provide feedback to large language models (LLMs). Given two alternative model responses to the same input, a human or AI annotator selects the "better" response.…

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary LLMs. However, many languages written in non-Latin scripts…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Enhancing the adaptive capabilities of large language models is a critical pursuit in both research and application. Traditional fine-tuning methods require substantial data and computational resources, especially for enhancing specific…

This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7). This task focuses on selecting the correct next utterance from a set of candidates given a partial…

Word embeddings learnt from large corpora have been adopted in various applications in natural language processing and served as the general input representations to learning systems. Recently, a series of post-processing methods have been…

The rapid adoption of large language models (LLMs) in customer service introduces new risks, as malicious actors can exploit them to conduct large-scale user impersonation through machine-generated text (MGT). Current MGT detection methods…

The integration of large language models (LLMs) into recommendation systems has revealed promising potential through their capacity to extract world knowledge for enhanced reasoning capabilities. However, current methodologies that adopt…

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Geo-textual objects, i.e., objects with both spatial and textual attributes, such as points-of-interest or web documents with location tags, are prevalent and fuel a range of location-based services. Existing spatial keyword querying…

Speech translation (ST) systems translate speech in one language to text in another language. End-to-end ST systems (e2e-ST) have gained popularity over cascade systems because of their enhanced performance due to reduced latency and…

We propose Dynamic Meta-Metrics (DMM), a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. Rather than relying on a single static ensemble or language-specific weighting,…

Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…

Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution…

Spotting user-defined/flexible keywords represented in text frequently uses an expensive text encoder for joint analysis with an audio encoder in an embedding space, which can suffer from heterogeneous modality representation (i.e., large…

Extractive question answering (QA) systems can enable physicians and researchers to query medical records, a foundational capability for designing clinical studies and understanding patient medical history. However, building these systems…

We consider real world task-oriented dialog settings, where agents need to generate both fluent natural language responses and correct external actions like database queries and updates. We demonstrate that, when applied to customer support…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…