8 papers
MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
Shihao Liu, Hao Yin, Lijun Liu +3
Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback…
MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking
HONOR Agentic Search Team, Zhengzong Chen, Lei Tang +27
We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamenta…
Can LLM Annotations Replace User Clicks for Learning to Rank?
Lulu Yu, Keping Bi, Jiafeng Guo +4
Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly. Click data has been widely used as a low-cost a…
Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation
Hengran Zhang, Minghao Tang, Keping Bi +5
This paper explores the use of large language models (LLMs) for annotating document utility in training retrieval and retrieval-augmented generation (RAG) systems, aiming to reduce…
Bacon-Shor Board Games
M. Sohaib Alam, Jun Zen, Thomas R. Scruby
We identify a period-4 measurement schedule for the checks of the Bacon-Shor code that fully covers spacetime with constant-weight detectors, and is numerically observed to provide…
Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance
Lulu Yu, Keping Bi, Jiafeng Guo +3
Most existing unbiased learning-to-rank (ULTR) approaches are based on the user examination hypothesis, which assumes that users will click a result only if it is both relevant and…
Generative Retrieval for Book search
Yubao Tang, Ruqing Zhang, Jiafeng Guo +5
In book search, relevant book information should be returned in response to a query. Books contain complex, multi-faceted information such as metadata, outlines, and main text, whe…
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
Yutong Wu, Di Huang, Wenxuan Shi +13
Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to…