7 papers
TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability
Krish Sharma, Omar Naim, Soumadeep Saha +3
Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we investigate when such improvements…
TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
Omar Naim, Krish Sharma, Niyar R Barman +1
Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (…
SSA: Improving Performance With a Better Scoring Function
Omar Naim, Swarnadeep Bhar, Jérôme Bolte +1
While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify…
COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following
Swarnadeep Bhar, Omar Naim, Eleni Metheniti +4
Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detect…
Analyzing limits for in-context learning
Omar Naim, Jerome Bolte, Nicholas Asher
Our paper challenges claims from prior research that transformer-based models, when learning in context, implicitly implement standard learning algorithms. We present empirical evi…
Re-examining learning linear functions in context
Omar Naim, Guilhem Fouilhé, Nicholas Asher
In-context learning (ICL) has emerged as a powerful paradigm for easily adapting Large Language Models (LLMs) to various tasks. However, our understanding of how ICL works remains…