9 papers
Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers
Haifeng Wu, Srinivasan Manoharan, Jian Wan +3
Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expensive: a zero-shot NLI classifie…
Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal Routing
Srinivasan Manoharan, Junhua Zhao, Fangbo Tu +6
Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer…
RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving
Haifeng Wu, Srinivasan Manoharan, Fangbo Tu +2
We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared…
Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation
Fangbo Tu, Junhua Zhao, Chi Liu +4
Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost constrained production enviro…
MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
Jyotika Singh, Fang Tu, Miguel Ballesteros +6
Large language models (LLMs) suffer significant performance degradation when user instructions and context are distributed over multiple conversational turns, yet multi-turn (MT) i…
GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations
Jyotika Singh, Fang Tu, Aziza Mirsaidova +11
Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness va…
JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
Sandip Ghoshal, Anshul Mittal, Jyotika Singh +9
Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptio…
DiffuMask: Diffusion Language Model for Token-level Prompt Pruning
Caleb Zheng, Jyotika Singh, Fang Tu +6
In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may co…
Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
Chi Liu, Xin Chen, Xu Zhou +2
Large Language Models (LLMs) have achieved remarkable success, underpinning diverse AI applications. However, they often suffer from performance degradation due to factors such as…