Tootfinder

from my link log —
Decomposing transactional systems.
https://transactional.blog/blog/2025-decomposing-transactional-systems
saved 2025-04-18

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- Learning Evaluation Models from Large Language Models for Sequence Generation
Wang, Zhou, Chang, Liu, Zhang, Du, Xiao, Zhang, Zhu
https://arxiv.org/abs/2308.04386 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/110858347619335772
- MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting
Hongda Sun, Hongzhan Lin, Haiyu Yan, Yang Song, Xin Gao, Rui Yan
https://arxiv.org/abs/2405.18113
- Capturing Style in Author and Document Representation
Enzo Terreau, Antoine Gourru, Julien Velcin
https://arxiv.org/abs/2407.13358 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/112811825734411424
- Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Perso...
Alireza Salemi, Hamed Zamani
https://arxiv.org/abs/2409.09510
- Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization
Alireza Salemi, Hamed Zamani
https://arxiv.org/abs/2410.09942 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113311129163471763
- A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao
https://arxiv.org/abs/2410.16155 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113350851853547191
- SceneGenAgent: Precise Industrial Scene Generation with Coding Agent
Xiao Xia, Dan Zhang, Zibo Liao, Zhenyu Hou, Tianrui Sun, Jing Li, Ling Fu, Yuxiao Dong
https://arxiv.org/abs/2410.21909 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113395761808224082
- Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages
Nguyen, Mahajan, Yadav, Salazar, Yu, Hashemi, Maheshwary
https://arxiv.org/abs/2411.02398 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113429970773753104
- CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
Leitian Tao, Xiang Chen, Tong Yu, Tung Mai, Ryan Rossi, Yixuan Li, Saayan Mitra
https://arxiv.org/abs/2411.05199 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113463056002627712
- OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50 Languages
Chester Palen-Michel, Maxwell Pickering, Maya Kruse, Jonne S\"alev\"a, Constantine Lignos
https://arxiv.org/abs/2412.09587 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113644218384986889
- Do Large Language Models Advocate for Inferentialism?
Yuzuki Arai, Sho Tsugawa
https://arxiv.org/abs/2412.14501 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113683825673436379
- Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Liao, Xu, Dong, Li, Monz, Savarese, Sahoo, Xiong
https://arxiv.org/abs/2501.19324 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/113938656684817759
- Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
Borkar, Jagielski, Lee, Mireshghallah, Smith, Choquette-Choo
https://arxiv.org/abs/2502.15680 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114057719598830407
- Evaluating Large Language Models for Automated Clinical Abstraction in Pulmonary Embolism Registr...
Alwakeel, Buck, Martin, Aslam, Rajagopal, Pei, Podgoreanu, Lindsell, Wong
https://arxiv.org/abs/2503.21004 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114238829015127676
- LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
Zou, Huang, Wu, Chen, Miao, Nguyen, Zhou, Zhang, Fang, He, Li, Li, Jiang, Liu, Yu
https://arxiv.org/abs/2505.00753 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114453994824459151
- Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs
Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, Xiang Wang
https://arxiv.org/abs/2505.11277 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114533276160074683
- A3 : an Analytical Low-Rank Approximation Framework for Attention
Wong, Zhang, Cao, Gimenes, Constantinides, Luk, Zhao
https://arxiv.org/abs/2505.12942 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114539100871221308
- Thinkless: LLM Learns When to Think
Gongfan Fang, Xinyin Ma, Xinchao Wang
https://arxiv.org/abs/2505.13379 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114539110987186123
- Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability ...
Zeinab Dehghani, Mohammed Naveed Akram, Koorosh Aslansefat, Adil Khan
https://arxiv.org/abs/2505.21657 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114589890676312038
toXiv_bot_toot

I am once again getting a wave of right-wing spam SMSes from Hillsdale College (purportedly). Are they actually letting their institution’s name be attached to political spam? I realize there are all kinds of super gross things about Hillsdale as an institution, but even so, I’d think the institution would want to preserve some shred of self-respect, or at least try to keep up appearances.
The spam links are all the domain rght.io followed by 6-character alphanumeric codes, such as:
http://rght.io/jjne75
http://rght.io/ip0l3b
http://rght.io/646anh
http://rght.io/aem0ai
http://rght.io/8gplnp
http://rght.io/mncl8i
http://rght.io/eo556l
http://rght.io/15bk46
http://rght.io/igd8ga
http://rght.io/pp2ggf
(Those are random examples, I don’t want them validating my number; I just want to send the typical Fedi server traffic their way.)
I haven’t investigated the domain, server, etc. at all, but if anyone is inspired…have at it!

https://techcrunch.com/2025/06/27/prolific-cybercrime-gang-now-targeting-airlines-and-the-transportation-sector/
Prolific cybercrime gang now targeting airlines and the transportation sector

Prolific cybercrime gang now targeting airlines and the transportation sector | TechCrunch
The fresh wave of attacks targeting airlines comes soon after the hackers hit the U.K. retail sector and the insurance industry.

Daylight #fireball over the U.S. Southeast - and there may have been a related meteorite hit of a house: https://www.youtube.com/watch?v=H_OaYXxB7Z8. Visual reports: https://fireballs.imo.net/members/imo_view/event/2025/3455. Detections by radar and from a satellite: https://x.com/spann/status/1938367055368970461. An article: https://eos.org/research-and-developments/fireball-passes-over-southeastern-united-states. More TV reports: https://www.youtube.com/watch?v=bq7THmDUCfg and https://www.youtube.com/watch?v=IcTk-Sg1uSA and https://www.youtube.com/watch?v=5d8HbC4zjKw

🚫 If you support J.K. Rowling and her transphobic views, you’re not welcome on my page.
🌈 I stand unapologetically with queer and trans people.
#LGBTQIA #TransRights #QueerCommunity

More of this, please. https://me.dm/@funcrunch/114751288573182357

South Korea police detain six Americans trying to send cash, rice to North Korea (Ju-min Park/Reuters)
https://www.reuters.com/world/asia-pacific/south-korea-police-detain-six-americans-trying-send-cash-rice-north-korea-2025-06-27/
http://www.memeorandum.com/250627/p153#a250627p153

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- CVC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Wu, Shen, Zhao, Wang, Dong, Shi, Lu, Zhao, Zeng
https://arxiv.org/abs/2506.01495 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114618448055956836
- Rethinking LLM Training through Information Geometry and Quantum Metrics
Riccardo Di Sipio
https://arxiv.org/abs/2506.15830 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114731686305319149
- Evaluating Rare Disease Diagnostic Performance in Symptom Checkers: A Synthetic Vignette Simulati...
Takashi Nishibayashi, Seiji Kanazawa, Kumpei Yamada
https://arxiv.org/abs/2506.19750 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114743481477368416
- SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Rerankin...
Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie
https://arxiv.org/abs/2506.20081 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114748542843447689
- TAPS: Tool-Augmented Personalisation via Structured Tagging
Ekaterina Taktasheva, Jeff Dalton
https://arxiv.org/abs/2506.20409 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114748913134606625
- DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
Shansan Gong, Ruixiang Zhang, Huangjie Zheng, Jiatao Gu, Navdeep Jaitly, Lingpeng Kong, Yizhe Zhang
https://arxiv.org/abs/2506.20639 initial toot: https://mastoxiv.page/@arXiv_csCL_bot/114749020616347454
- HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su, Shang-Hong Lai, Winston H. Hsu
https://arxiv.org/abs/2408.17443 initial toot: https://mastoxiv.page/@arXiv_csCV_bot/113066937441197298
- Simulating Hard Attention Using Soft Attention
Andy Yang, Lena Strobl, David Chiang, Dana Angluin
https://arxiv.org/abs/2412.09925 initial toot: https://mastoxiv.page/@arXiv_csLG_bot/113661239851327922
- GroundCap: A Visually Grounded Image Captioning Dataset
Daniel A. P. Oliveira, Louren\c{c}o Teodoro, David Martins de Matos
https://arxiv.org/abs/2502.13898 initial toot: https://mastoxiv.page/@arXiv_csCV_bot/114035055313760626
- PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
Feng Ni, Kui Huang, Yao Lu, Wenyu Lv, Guanzhong Wang, Zeyu Chen, Yi Liu
https://arxiv.org/abs/2503.04065 initial toot: https://mastoxiv.page/@arXiv_csCV_bot/114119989776826725
- Exploring Big Five Personality and AI Capability Effects in LLM-Simulated Negotiation Dialogues
Myke C. Cohen, Zhe Su, Hsien-Te Kao, Daniel Nguyen, Spencer Lynch, Maarten Sap, Svitlana Volkova
https://arxiv.org/abs/2506.15928 initial toot: https://mastoxiv.page/@arXiv_csAI_bot/114732117548357630
- From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
Weizhi Zhang, et al.
https://arxiv.org/abs/2506.18959 initial toot: https://mastoxiv.page/@arXiv_csIR_bot/114742918525916709
toXiv_bot_toot