Related papers: BEIR-PL: Zero Shot Information Retrieval Benchmark…

Multi-label requirements classification is a challenging task, especially when dealing with numerous classes at varying levels of abstraction. The difficulties increases when a limited number of requirements is available to train a…

Language agnostic and semantic-language information isolation is an emerging research direction for multilingual representations models. We explore this problem from a novel angle of geometric algebra and semantic space. A simple but highly…

The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with…

Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often…

Evaluation in Information Retrieval relies on post-hoc empirical procedures, which are time-consuming and expensive operations. To alleviate this, Query Performance Prediction (QPP) models have been developed to estimate the performance of…

We present Mr. TyDi, a multi-lingual benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages, designed to evaluate ranking with learned dense representations. The goal of this resource is to spur research in…

Current Large Language Models (LLMs) have shown strong reasoning capabilities in commonsense question answering benchmarks, but the process underlying their success remains largely opaque. As a consequence, recent approaches have equipped…

In this paper, we ask: what truly determines the effectiveness of RL training data for enhancing language models' reasoning capabilities? While recent advances like o1, Deepseek R1, and Kimi1.5 demonstrate RL's potential, the lack of…

Large Language Models (LLMs) often show reduced performance, cultural alignment, and safety robustness in non-English languages, partly because English dominates both pre-training data and human preference alignment datasets. Training…

Aligning large language models (LLMs) with human preferences has achieved remarkable success. However, existing Chinese preference datasets are limited by small scale, narrow domain coverage, and lack of rigorous data validation.…

Imagine a language with masculine, feminine, and neuter grammatical genders, yet, due to historical and political conventions, masculine forms are predominantly used to refer to men, women and mixed-gender groups. This is the reality of…

We present Bielik 11B v2, a state-of-the-art language model optimized for Polish text processing. Built on the Mistral 7B v0.2 architecture and scaled to 11B parameters using depth up-scaling, this model demonstrates exceptional performance…

While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the use of large neural architectures and the application of…

Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search…

Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural language. Traditionally, models designed for CIR have…

Privacy Masking is a critical concept under data privacy involving anonymization and de-anonymization of personally identifiable information (PII). Privacy masking techniques rely on Named Entity Recognition (NER) approaches under NLP…

Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT), have shown success in a variety of zero-shot cross-lingual tasks. However, these models are limited by having inconsistent contextualized representations of…

Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text…

Modern open-domain question answering systems often rely on accurate and efficient retrieval components to find passages containing the facts necessary to answer the question. Recently, neural retrievers have gained popularity over lexical…

Language models have the potential to assess mental health using social media data. By analyzing online posts and conversations, these models can detect patterns indicating mental health conditions like depression, anxiety, or suicidal…