Skip to content
Papers.

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs research paper by Cohere, 2025

Cohere · Jun 25, 2025 · Inference and efficiency · 11 upvotes 1 year ago

Read on arXiv

What it shows

The study examines and proposes new sampling and selection strategies to enhance inference-time compute for multilingual and multi-task large language models, demonstrating significant improvements in win-rates across various languages and tasks.

Hugging Face's summary; not yet checked by hand.

More from Cohere

All 30
PaperCitations
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language ReasoningOptimized supervised fine-tuning data composition enables reasoning models to consistently process and respond in diverse non-English languages without requiring reasoning supervision in each target language.Reasoning · Sep 20262 weeks ago-
The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic ReasoningAn open competition on unseen Linguistics Olympiad puzzles, graded by the official jury; small 14B systems beat models twice their size.Reasoning · Aug 20265 weeks ago-
CALIBER: Calibrating Confidence Before and After Reasoning in Language ModelsTrains reasoning models to state their confidence twice, before thinking and after answering, halving calibration error against the best single-estimate method.Reasoning · Jun 20263 months ago-
AI Exposure Scores: what they measure, what they miss, and what comes nextReviews how widely cited scores of which jobs AI can assist are used in policy, what they miss, and newer measures that address it.Foundation models · Jun 20263 months ago-
The Culture Funnel: You Can't Align What isn't in the DataModern LLM pipelines experience a cultural data funnel where explicit cultural signals diminish during post-training, necessitating shifts in training data approaches for better cultural alignment.Alignment and safety · Jun 20263 months ago-
Soft-SVeRL: Self-Verified Reinforcement Learning with Soft RewardsTurns each prompt into a checklist scored item by item, giving reinforcement learning partial-credit rewards for tasks that cannot be checked automatically.Foundation models · May 20264 months ago-
Agents Explore but Agents Ignore: LLMs Lack Environmental CuriosityLLM-based agents fail to exploit discovered unexpected information despite recognizing it, indicating a lack of environmental curiosity that depends on tools, compute, and training data distribution.Agents and evaluation · Apr 20265 months ago-
Tiny Aya: Bridging Scale and Multilingual DepthTiny Aya demonstrates high-quality multilingual capabilities with 3.35 billion parameters through region-aware posttraining and balanced language performance.Training and scaling · Mar 20266 months ago-

Other inference and efficiency papers

Topic
PaperCitations
Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley · Sep 20233 years ago8,481
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessFlashAttention computes exact attention with far fewer GPU memory reads and writes, making long sequences faster.Stanford University · May 20224 years ago5,334
Group Sequence Policy OptimizationGroup Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.Alibaba (Qwen) · Jul 2025 · Unverified1 year ago688
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.DeepSeek · Feb 2025 · Unverified1 year ago507
SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.Hugging Face · Apr 2025 · Unverified1 year ago294
Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.DeepSeek · Apr 2025 · Unverified1 year ago249
About this paper
Authors
Ammar Khairi, Daniel D'souza, Ye Shen and 2 more
arXiv
2506.20544 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
11 · Hugging Face
Lab
Cohere · on Companies · on Acquisitions · on Releases

Changes

What changed
New paperAdded to the listSep 26, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.