HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation
arXiv:2506.21546v1 Announce Type: cross Abstract: Recent progress in vision-language segmentation has significantly advanced grounded visual understanding. However, these models often ...
Read more
[2410.19494] Graph Linearization Methods for Reasoning on Graphs with Large Language Models
[Submitted on 25 Oct 2024 (v1), last revised 25 Jun 2025 (this version, v3)] View a PDF of the paper ...
Read more
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
arXiv:2506.19697v1 Announce Type: cross Abstract: Extreme activation outliers in Large Language Models (LLMs) critically degrade quantization performance, hindering efficient on-device ...
Read more
TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems
arXiv:2506.19441v1 Announce Type: cross Abstract: Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as ...
Read more
Programming by Backprop: LLMs Acquire Reusable Algorithmic Abstractions During Code Training
arXiv:2506.18777v1 Announce Type: cross Abstract: Training large language models (LLMs) on source code significantly enhances their general-purpose reasoning abilities, but ...
Read more
AI-Generated Song Detection via Lyrics Transcripts
arXiv:2506.18488v1 Announce Type: cross Abstract: The recent rise in capabilities of AI-based music generation tools has created an upheaval in ...
Read more
An Interactive Benchmark for Evaluating LLMs’ Sequential Reasoning Ability
[Submitted on 14 Feb 2024 (v1), last revised 20 Jun 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2504.21016] Nested Named-Entity Recognition on Vietnamese COVID-19: Dataset and Experiments
[Submitted on 21 Apr 2025 (v1), last revised 14 Jun 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2502.14718] Entity Framing and Role Portrayal in the News
[Submitted on 20 Feb 2025 (v1), last revised 15 Jun 2025 (this version, v2)] Authors:Tarek Mahmoud, Zhuohan Xie, Dimitar Dimitrov, ...
Read more
On the Performance of LLMs for Real Estate Appraisal
arXiv:2506.11812v1 Announce Type: cross Abstract: The real estate market is vital to global economies but suffers from significant information asymmetry. ...
Read more
