Large Language Models

Top-ησ: A novel LLM sampling method outperforms existing approaches by using a statistical threshold on pre-softmax logits, achieving higher accuracy while maintaining diversity, even at high temperat…

LLMs can now self-improve long-context reasoning via SEALONG, a novel method leveraging multiple model outputs and minimum Bayes risk scoring to enable effective supervised fine-tuning or preference o…

Feature-level constrained Preference Optimization (FPO) boosts LLM alignment efficiency and stability by using sparse autoencoders and feature-level constraints, achieving significant improvements ove…

Larger language models aren’t always better teachers for instruction tuning; a new metric, CAR, predicts teacher model effectiveness better than existing methods.

Chinese SimpleQA, a new benchmark, offers a comprehensive evaluation of the factuality of LLMs answering short questions in Chinese, exhibiting diversity, high quality, and ease of evaluation.

WEB-DREAMER uses LLMs as world models for safe and efficient web agent planning, achieving substantial performance gains over reactive baselines.

Contrary to common belief, toxicity reduction in language models isn’t simply achieved by dampening toxic neurons; it’s a complex balancing act across multiple neuron groups.

IOPO empowers LLMs to master complex instructions via input-output preference optimization, boasting significant performance gains on a new benchmark, TRACE.

Golden Touchstone, a new bilingual benchmark, comprehensively evaluates financial LLMs across eight tasks, revealing model strengths and weaknesses and advancing FinLLM research.

Boost large language model training speed by 51% with Vocabulary Parallelism, a novel technique that balances computation and memory usage across pipeline stages.

OpenCoder, a top-tier open-source code LLM, is introduced, providing not only model weights and code but also reproducible training data, data processing pipelines, and training protocols, enabling co…

Can LLMs effectively handle information spread across vast, almost million-scale datasets? This research investigates this question by evaluating 17 LLMs on novel ‘needle threading’ tasks. These task…

Researchers developed Hardware and Software Platform Inference (HSPI) to identify the underlying GPU and software stack used to serve LLMs, enhancing transparency in the industry.

DELIFT: Data Efficient Language Model Instruction Fine-Tuning, drastically reduces the data needed for effective LLM fine-tuning without sacrificing performance.

BitNet a4.8 achieves comparable performance to existing 1-bit LLMs, but with significantly faster inference, by using a hybrid quantization and sparsification strategy for 4-bit activations.

Zebra-Llama, a context-aware LLM, democratizes rare disease knowledge by providing highly precise, context-rich information about Ehlers-Danlos Syndrome, significantly improving diagnostic support.

WEBRL: A self-evolving online curriculum reinforcement learning framework empowers open LLMs to excel as high-performing web agents, surpassing proprietary models.

Researchers discovered predictable scaling laws for activation sparsity in LLMs, showing how data, architecture, and model size influence sparsity, paving the way for more efficient and interpretable …

Boosting unit test generation efficiency, this study empirically evaluates various parameter-efficient fine-tuning methods on LLMs, demonstrating comparable performance to full fine-tuning at signific…

Tencent unveils Hunyuan-Large, a groundbreaking open-source MoE LLM boasting 389B parameters and 52B activated parameters, surpassing existing models in performance across various benchmarks.