activity
20242026
collaborators
Showing cs.CLShow all

25 papers · 1 filter

cs.CL2026

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt

"Talk short. Drop grammar. Save token." This caveman style is widely promoted as a way to cut inference cost, but whether it actually saves anything depends on which channel (the u…

cs.CL2026

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli +7

Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level m…

cs.CL2026

Lizard: An Efficient Linearization Framework for Large Language Models

Chien Van Nguyen, Huy Nguyen, Ruiyi Zhang +10

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe co…

cs.CL2026

Structured Uncertainty guided Clarification for LLM Agents

Manan Suri, Puneet Mathur, Nedim Lipka +3

LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches ope…

cs.CL2026

Cluster-R1: Large Reasoning Models Are Instruction-following Clustering Agents

Peijun Qing, Puneet Mathur, Nedim Lipka +5

General-purpose embedding models excel at recognizing semantic similarities but fail to capture the characteristics of texts specified by user instructions. In contrast, instructio…

cs.CL2026

Steering MoE LLMs via Expert (De)Activation

Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy +5

Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a fra…