Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
arXiv:2512.10422v2 Announce Type: replace-cross Abstract: Since large language models (LLMs) have a tendency to generate factually inaccurate output, retrieval-augmented generation…
CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound
arXiv:2512.11169v1 Announce Type: new Abstract: Combinatorial sequential decision making problems are typically modeled as mixed integer linear programs (MILPs) and…
Decoupled Q-Chunking
arXiv:2512.10926v2 Announce Type: replace-cross Abstract: Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future…
Grammar-Aligned Decoding
arXiv:2405.21047v3 Announce Type: replace Abstract: Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code,…
AI and Jobs: Has the Inflection Point Arrived? Evidence from an Online Labor Platform
arXiv:2312.04180v3 Announce Type: replace Abstract: This study investigates how artificial intelligence (AI) influences various online labor markets (OLMs) over time.…
Textual Data Bias Detection and Mitigation — An Extensible Pipeline with Experimental Evaluation
arXiv:2512.10734v2 Announce Type: replace-cross Abstract: Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful…