Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment

[Submitted on 29 Sep 2025 (v1), last revised 30 Sep 2025 (this version, v2)] Authors:Liang Lin, Zhihao Xu, Junhao Dong, ...
Read more
Auditing Contextual Privacy in LLM Agents

[Submitted on 11 Jun 2025 (v1), last revised 27 Sep 2025 (this version, v3)] View a PDF of the paper ...
Read more
[2412.01752] A Neurosymbolic Fast and Slow Architecture for Graph Coloring

[Submitted on 2 Dec 2024 (v1), last revised 29 Sep 2025 (this version, v2)] View a PDF of the paper ...
Read more
A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation

[Submitted on 22 May 2025 (v1), last revised 25 Sep 2025 (this version, v2)] View a PDF of the paper ...
Read more
An Adaptive Self-Correction Chain-of-Thought Method for Late-Stage Fragility in LLMs

[Submitted on 7 Aug 2025 (v1), last revised 26 Sep 2025 (this version, v3)] View a PDF of the paper ...
Read more
[2502.18179] Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs

[Submitted on 25 Feb 2025 (v1), last revised 25 Sep 2025 (this version, v3)] View a PDF of the paper ...
Read more
An Environment for Exploring Learning Through Conversational Interaction

[Submitted on 11 Apr 2025 (v1), last revised 24 Sep 2025 (this version, v3)] Authors:Nicola Horst, Davide Mazzaccara, Antonia Schmidt, ...
Read more
Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering

[Submitted on 26 Feb 2025 (v1), last revised 24 Sep 2025 (this version, v3)] View a PDF of the paper ...
Read more
A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages

[Submitted on 22 Aug 2025 (v1), last revised 23 Sep 2025 (this version, v4)] View a PDF of the paper ...
Read more
BoostCD and Its Application to Information Extraction

[Submitted on 17 Jun 2025 (v1), last revised 22 Sep 2025 (this version, v2)] View a PDF of the paper ...
Read more