相关论文: Don't Retrieve, Generate: Prompting LLMs for Synth…

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs)…

Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memories. However, due to the paradigm discrepancy between text…

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Information Retrieval (IR) is fundamental to many modern NLP applications. The rise of dense retrieval (DR), using neural networks to learn semantic vector representations, has significantly advanced IR performance. Central to training…

When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs)…

Hard negative sampling improves recommendation performance by accelerating convergence and sharpening the decision boundary. However, most existing methods rely on heuristic strategies, selecting negatives from a fixed candidate pool.…

For researchers leveraging Large-Language Models (LLMs) in the generation of training datasets, especially for conversational recommender systems - the absence of robust evaluation frameworks has been a long-standing problem. The efficiency…

Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models…

Current disfluency detection methods heavily rely on costly and scarce human-annotated data. To tackle this issue, some approaches employ heuristic or statistical features to generate disfluent sentences, partially improving detection…

Large Language Models (LLMs) have performed well on various reasoning tasks, but their inaccessibility and numerous parameters hinder wide application in practice. One promising way is distilling the reasoning ability from LLMs to small…

Although Large Language Models (LLMs) exhibit remarkable adaptability across domains, these models often fall short in structured knowledge extraction tasks such as named entity recognition (NER). This paper explores an innovative,…

Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated…

While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically examines how…

There has been limited success for dense retrieval models in multilingual retrieval, due to uneven and scarce training data available across multiple languages. Synthetic training data generation is promising (e.g., InPars or Promptagator),…

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Causality detection and mining are important tasks in information retrieval due to their enormous use in information extraction, and knowledge graph construction. To solve these tasks, in existing literature there exist several solutions --…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research…

In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address this limitation,…

Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data. However, distilled models do not match the effectiveness of their teacher LLMs. We…