MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.
hub Canonical reference
Crosslingual generalization through multitask finetuning
Canonical reference. 83% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6representative citing papers
Language representations serve as the asymptotic attractor for convergence in independently trained multimodal neural networks due to feature density asymmetry.
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
C-Pack releases a new Chinese embedding benchmark, large training dataset, and optimized models that outperform priors by up to 10% on C-MTEB while also delivering English SOTA results.
WattLayer is a layer-wise energy estimation model achieving 19.6% median error on over 100k layers from 295 architectures across 3 tasks and 3 platforms, with generalization to new tasks via shared layers.
Manual audit shows web-scraped Lombard corpora are largely noisy and biased toward Western varieties over Eastern ones.
Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.
Routing architecture for MLLMs enables continual learning with constant compute, matching multi-task learning performance and supporting cross-modal transfer.
MiniMax-01 models match GPT-4o and Claude-3.5-Sonnet performance while providing 20-32 times longer context windows through lightning attention and MoE scaling.
StarCoder2-15B matches or beats CodeLlama-34B on code tasks despite being smaller, and StarCoder2-3B outperforms prior 15B models, with open weights and exact training data identifiers released.
Factually Augmented RLHF aligns large multimodal models to reduce hallucinations, reaching 94% of GPT-4 on LLaVA-Bench and 60% improvement on the new MMHAL-BENCH.
Repeating training data up to 4 epochs yields negligible loss increase versus unique data for fixed compute, and a new scaling law accounts for the decaying value of repeated tokens and excess parameters.
The Flan Collection demonstrates that task balancing, data enrichment, and mixed prompt training are critical to effective instruction tuning, yielding stronger Flan-T5 models released publicly.
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
XTransplant empirically shows that cross-lingual latent transplantation yields mutual benefits for multilingual capability and cultural adaptability in LLMs, especially low-resource ones, while revealing underutilized model potential.
Open-source multilingual E5 embedding models are trained via contrastive pre-training on 1 billion text pairs and fine-tuning, with an instruction-tuned model matching English SOTA performance.
Empirical tests show LLMs from 1B to 7B parameters exhibit catastrophic forgetting during continual instruction tuning, with forgetting severity increasing with scale and decoder-only models retaining more than encoder-decoder models.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
Position paper warns that model collapse in self-consuming multilingual LLM training loops risks flattening linguistic diversity and cultural nuance.
A framework is described for adapting six LLMs to transportation engineering via LoRA-based continued pretraining on domain documents, with two models showing strongest results on BLEU-4 and ROUGE metrics.
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.