activity
20242026
collaborators

11 papers

cs.CL2026

Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size

Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5

Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…

cs.DC2026

Training LLMs with Fault Tolerant HSDP on 100,000 GPUs

Omkar Salpekar, Rohan Varma, Kenny Yu +20

Large-scale training systems typically use synchronous training, requiring all GPUs to be healthy simultaneously. In our experience training on O(100K) GPUs, synchronous training r…

cs.CL2025

LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch

Jan Pfister, Julia Wunderle, Andreas Hotho

We create two German-only decoder models, LLäMmlein 120M and 1B, transparently from scratch and publish them, along with the training data, for the German NLP research community t…

cs.CL2025

Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems

Shang-Chi Tsai, Yun-Nung Chen

With the advancement of large language models, many dialogue systems are now capable of providing reasonable and informative responses to patients' medical conditions. However, whe…

cs.LG2025

Compute Optimal Scaling of Skills: Knowledge vs Reasoning

Nicholas Roberts, Niladri Chatterji, Sharan Narang +2

Scaling laws are a critical component of the LLM development pipeline, most famously as a way to forecast training decisions such as 'compute-optimally' trading-off parameter count…

cs.CL2025

Jailbreak Distillation: Renewable Safety Benchmarking

Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…