13 papers
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
Sichun Luo, Yi Huang, Guanzhi Deng +6
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.…
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
Haochen Luo, Yi Huang, Sichun Luo +5
Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-…
SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
Sichun Luo, Yi Huang, Haochen Luo +7
Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through execu…
CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases
Xiaona Xue, Yiqiao Huang, Jiacheng Li +9
Enhancing the ability of large language models (LLMs) to follow complex instructions is critical for their deployment in real-world applications. However, existing evaluation metho…
ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models
Sichun Luo, Yi Huang, Mukai Li +5
Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or ambiguous informati…
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
Fengyuan Liu, Yi Huang, Sichun Luo +6
Discovering effective predictive signals, or "alphas," from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despit…
Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems
Yucheng Cai, Yuxuan Wu, Yi Huang +2
Large language models (LLMs) have recently been applied to dialog systems. Despite making progress, LLMs are prone to errors in knowledge-intensive scenarios. Recently, approaches…
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems
Yucheng Cai, Ke Li, Yi Huang +2
A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers…
From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM
Jianyu Liu, Yi Huang, Sheng Bi +2
In a conversational system, dynamically generating follow-up questions based on context can help users explore information and provide a better user experience. Humans are usually…
Palette of Language Models: A Solver for Controlled Text Generation
Zhe Yang, Yi Huang, Yaqin Chen +3
Recent advancements in large language models have revolutionized text generation with their remarkable capabilities. These models can produce controlled texts that closely adhere t…
Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs
Yu Li, Yi Huang, Guilin Qi +7
Knowledge graphs are widely used in industrial applications, making error detection crucial for ensuring the reliability of downstream applications. Existing error detection method…
The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)
Yucheng Cai, Si Chen, Yuxuan Wu +3
Recently, increasing research interests have focused on retrieval augmented generation (RAG) to mitigate hallucination for large language models (LLMs). Following this trend, we la…
Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking
Hong Liu, Yucheng Cai, Yuan Zhou +3
Continual learning is crucial for dialog state tracking (DST) in dialog systems, since requirements from users for new functionalities are often encountered. However, most of exist…