9 papers
TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
Vansh Kapoor, Aman Gupta, Hao Chen +3
Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to complete solution breakdown. Current LLM r…
TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues
Sarik Ghazarian, Abhinav Gullapalli, Swair Shah +4
In real-world task-oriented dialogue (TOD) settings, agents are required to strictly adhere to complex instructions while conducting multi-turn conversations with customers. These…
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Chenlu Ye, Zhou Yu, Ziji Zhang +5
Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards…
How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting
Aman Gupta, Yingying Zhuang, Zhou Yu +2
Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retr…
Multilingual Information Retrieval with a Monolingual Knowledge Base
Yingying Zhuang, Aman Gupta, Anurag Beniwal
Multilingual information retrieval has emerged as powerful tools for expanding knowledge sharing across languages. On the other hand, resources on high quality knowledge base are o…
REIC: RAG-Enhanced Intent Classification at Scale
Ziji Zhang, Michael Yang, Zhiyu Chen +6
Accurate intent classification is critical for efficient routing in customer service, ensuring customers are connected with the most suitable agents while reducing handling times a…
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
Xiaomin Li, Zhou Yu, Zhiwei Zhang +5
Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on man…
Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs
Xiaomin Li, Zhou Yu, Ziji Zhang +4
Large language models (LLMs) have demonstrated remarkable performance across diverse tasks by encoding vast amounts of factual knowledge. However, they are still prone to hallucina…
DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems
Aman Gupta, Anirudh Ravichandran, Ziji Zhang +3
Task-oriented dialogue systems are essential for applications ranging from customer service to personal assistants and are widely used across various industries. However, developin…