1

Sample compression unleashed: New generalization bounds for real valued losses
The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the …
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference …
Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework
Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in …
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT …
Prompting with Phonemes: Enhancing LLM Multilinguality for non-Latin Script Languages
Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script …
Generating a Low-code Complete Workflow via Task Decomposition and RAG
AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, …
Unpacking Trust Dynamics in the LLM Supply Chain: An Empirical Exploration to Foster Trustworthy LLM Production & Use
Research on trust in AI is limited to several trustors (e.g., end-users) and trustees (especially AI systems), and empirical …
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
Data analytics is essential for extracting valuable insights from data that can assist organizations in making effective decisions. We …
MMTEB: Massive Multilingual Text Embedding Benchmark

Text embeddings are typically evaluated on a narrow set of tasks, limited in terms of languages, domains, and task types. To circumvent …