69 citations · 90 across the 11 of their papers we have counts for
8 papers · 1 filter
Deconstructing In-Context Learning: Understanding Prompts via Corruption
Namrata Shivagunde, Vladislav Lialin, Sherin Muckatira +1
The ability of large language models (LLMs) to learn in context based on the provided prompt has led to an explosive growth in their use, culminating in the proliferation of…
Emergent Abilities in Reduced-Scale Generative Language Models
Sherin Muckatira, Vijeta Deshpande, Vladislav Lialin +1
Large language models can solve new tasks without task-specific fine-tuning. This ability, also known as in-context learning (ICL), is considered an emergent ability and is primari…
Let's Reinforce Step by Step
Sarah Pan, Vladislav Lialin, Sherin Muckatira +1
While recent advances have boosted LM proficiency in linguistic benchmarks, LMs consistently struggle to reason correctly on complex tasks like mathematics. We turn to Reinforcemen…
ReLoRA: High-Rank Training Through Low-Rank Updates
Vladislav Lialin, Namrata Shivagunde, Sherin Muckatira +1
Despite the dominance and effectiveness of scaling, resulting in large networks with hundreds of billions of parameters, the necessity to train overparameterized models remains poo…
Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale
Vijeta Deshpande, Dan Pechi, Shree Thatte +2
In recent years, language models have drastically grown in size, and the abilities of these models have been shown to improve with scale. The majority of recent scaling laws studie…
Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning
Namrata Shivagunde, Vladislav Lialin, Anna Rumshisky
Language model probing is often used to test specific capabilities of models. However, conclusions from such studies may be limited when the probing benchmarks are small and lack s…
Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
Vladislav Lialin, Vijeta Deshpande, Xiaowei Yao +1
This paper presents a systematic overview of parameter-efficient fine-tuning methods, covering over 50 papers published between early 2019 and mid-2024. These methods aim to addres…
NarrativeTime: Dense Temporal Annotation on a Timeline
Anna Rogers, Marzena Karpinska, Ankita Gupta +3
For the past decade, temporal annotation has been sparse: only a small portion of event pairs in a text was annotated. We present NarrativeTime, the first timeline-based annotation…