Natural Language Processing

GeAR, a new retrieval model, boosts accuracy by combining document retrieval with fine-grained information generation, leading to better understanding and improved localization.

BoostStep enhances large language models’ mathematical abilities by refining single-step reasoning through a novel step-level in-context learning strategy, achieving significant improvements on variou…

ToolHop: New benchmark dataset rigorously evaluates LLMs’ multi-hop tool use, revealing significant challenges and variations across different LLM families.

Unlocking LLM potential: This paper surveys test-time computing, showing how it boosts reasoning abilities by shifting from reactive System-1 to deliberate System-2 thinking, paving the way for more p…

New scaling laws for efficient floating-point quantization training in LLMs are presented, showing optimal bit allocation and critical data size.

REINFORCE++, a novel RLHF algorithm, achieves superior training stability and computational efficiency compared to existing methods like PPO and GRPO, while maintaining comparable performance.

Personalized Graph-based Retrieval-Augmented Generation (PGraphRAG) significantly improves personalized text generation by leveraging user-centric knowledge graphs, especially in cold-start scenarios …

METAGENE-1, a 7-billion parameter language model, achieves state-of-the-art results in pathogen detection and genomic embedding by leveraging a massive wastewater metagenomic dataset.

AUTO-RT automates LLM vulnerability discovery by using reinforcement learning to optimize complex attack strategies, achieving faster detection and higher success rates than existing methods.

Boosting code generation accuracy with more unit tests! This research shows that increasing the number of unit tests used to evaluate code generated by LLMs significantly improves accuracy, especially…

CODEELO benchmark uses CodeForces to fairly evaluate LLMs’ coding abilities, providing human-comparable Elo ratings and addressing limitations of existing benchmarks.

BoxingGym: A new benchmark rigorously evaluates AI agents’ ability to design experiments and discover scientific models, revealing current LLMs’ limitations and highlighting fertile research avenues.

LUSIFER: a novel zero-shot approach empowers English-centric LLM embedding models for multilingual tasks without explicit multilingual training data, significantly enhancing performance, especially fo…

Polarizing SSMs’ state transition matrices enhances long-range dependency modeling by mitigating recency bias and over-smoothing.

TANGOFLUX: Blazing-fast, high-fidelity text-to-audio generation using novel CLAP-Ranked Preference Optimization.

MAPQATOR: a web app that streamlines creation of reproducible geospatial QA datasets, boosting annotation speed by 30x!

New benchmarks, HumanEval Pro and MBPP Pro, reveal LLMs struggle with self-invoking code generation, highlighting a critical gap in current code reasoning capabilities.

Researchers introduce Learned Embedding Propagation (LEP), a novel technique that efficiently adapts large language models (LLMs) to new languages using minimal training data, thus overcoming limitati…

Dynasor optimizes LLM reasoning by dynamically allocating compute based on a novel ‘certaindex’ metric, reducing compute by up to 50% and increasing query rates by 3.3x.

OneKE: a dockerized, schema-guided LLM agent system efficiently extracts knowledge from diverse sources, offering adaptability and robust error handling.