Related papers: STRUM-LLM: Attributed and Structured Contrastive S…

Query-driven recommendation with unknown items poses a challenge for users to understand why certain items are appropriate for their needs. Query-driven Contrastive Summarization (QCS) is a methodology designed to address this issue by…

Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework called STRUX, which enhances LLM decision-making by providing…

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent…

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to…

Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Recent studies have found that summaries generated by large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. Therefore, we study an LLM-as-reference…

Accurate and complete product descriptions are crucial for e-commerce, yet seller-provided information often falls short. Customer reviews offer valuable details but are laborious to sift through manually. We present PRAISE: Product Review…

Knowledge distillation offers a transformative pathway to developing powerful, yet efficient, small language models (SLMs) suitable for resource-constrained environments. In this paper, we benchmark the performance and computational cost of…

In this paper, we present a conceptually simple while empirically powerful framework for abstractive summarization, SimCLS, which can bridge the gap between the learning objective and evaluation metrics resulting from the currently…

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…

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…

Small language models (SLMs), such as BART, can achieve summarization performance comparable to large language models (LLMs) via distillation. However, existing LLM-based ranking strategies for summary candidates suffer from instability,…

We propose STRuCT-LLM, a unified framework for training large language models (LLMs) to perform structured reasoning over both relational and graph-structured data. Our approach jointly optimizes Text-to-SQL and Text-to-Cypher tasks using…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…

Across all fields of academic study, experts cite their sources when sharing information. While large language models (LLMs) excel at synthesizing information, they do not provide reliable citation to sources, making it difficult to trace…

Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract…

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…