Related papers: A Simple and Effective Method To Eliminate the Sel…
Cross-lingual information retrieval is a challenging task in the absence of aligned parallel corpora. In this paper, we address this problem by considering topically aligned corpora designed for evaluating an IR setup. To emphasize, we…
Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech…
Debiasing techniques such as SentDebias aim to reduce bias in large language models (LLMs). Previous studies have evaluated their cross-lingual transferability by directly applying these methods to LLM representations, revealing their…
Negation is a fundamental aspect of human communication, yet it remains a challenge for Language Models (LMs) in Information Retrieval (IR). Despite the heavy reliance of modern neural IR systems on LMs, little attention has been given to…
Language identification (LID) is a critical step in curating multilingual LLM pretraining corpora from web crawls. While many studies on LID model training focus on collecting diverse training data to improve performance, low-resource…
Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such…
Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the…
This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…
Multilingual Information Retrieval is increasingly important in real-world search settings, where users issue queries over mixed-language corpora. Existing evaluations mainly reward language-agnostic semantic relevance, treating relevant…
Language Identification (LID) is the task of determining the language of a given text and is a fundamental preprocessing step that affects the reliability of downstream NLP applications. While recent work has expanded LID coverage for…
Trained on a vast amount of data, Large Language models (LLMs) have achieved unprecedented success and generalization in modeling fairly complex textual inputs in the abstract space, making them powerful tools for zero-shot learning. Such…
Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model…
Data is stored in both structured and unstructured form. Querying both, to power natural language conversations, is a challenge. This paper introduces dIR, Discrete Information Retrieval, providing a unified interface to query both free…
Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning…
Informal transliteration from other languages to English is prevalent in social media threads, instant messaging, and discussion forums. Without identifying the language of such transliterated text, users who do not speak that language…
In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their…
Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…
In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs), allowing them to adapt to new tasks by leveraging task-specific examples without updating model parameters. However, ICL faces challenges with increasing…
Semantic role labeling (SRL) identifies predicate-argument structure(s) in a given sentence. Although different languages have different argument annotations, polyglot training, the idea of training one model on multiple languages, has…
Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs). The emergence of large language…