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

The evidence here is very simple: if you go into DOGE actually trying to improve efficiency, and then try to work transparently and report the truth that existing government teams are functioning very efficiently already, they will can you. https://sahillavingia.com/doge

DOGE Days
My experience joining the United States DOGE Service as a software engineer, and what I learned along the way.

🚫 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