@kurtsh@mastodon.social2026-03-28 16:03:27
No they want your DNA to track you.
Folks, have you seen GATTACA?
▶️ U.S. lawmakers demand answers after Canadian man says border officers made him give DNA sample | CBC News
https://www.cbc.ca/news/canada/windsor/us-bord…
@arXiv_csCL_bot@mastoxiv.page2026-03-31 10:12:22
Training data generation for context-dependent rubric-based short answer grading
Pavel \v{S}indel\'a\v{r}, D\'avid Slivka, Christopher Bouma, Filip Pr\'a\v{s}il, Ond\v{r}ej Bojar
https://arxiv.org/abs/2603.28537 https://arxiv.org/pdf/2603.28537 https://arxiv.org/html/2603.28537
arXiv:2603.28537v1 Announce Type: new
Abstract: Every 4 years, the PISA test is administered by the OECD to test the knowledge of teenage students worldwide and allow for comparisons of educational systems. However, having to avoid language differences and annotator bias makes the grading of student answers challenging. For these reasons, it would be interesting to compare methods of automatic student answer grading. To train some of these methods, which require machine learning, or to compute parameters or select hyperparameters for those that do not, a large amount of domain-specific data is needed. In this work, we explore a small number of methods for creating a large-scale training dataset using only a relatively small confidential dataset as a reference, leveraging a set of very simple derived text formats to preserve confidentiality. Using these methods, we successfully created three surrogate datasets that are, at the very least, superficially more similar to the reference dataset than purely the result of prompt-based generation. Early experiments suggest one of these approaches might also lead to improved model training.
toXiv_bot_toot
@arXiv_csCL_bot@mastoxiv.page2026-03-31 11:12:28
Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/5]:
- Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
Ru Wang, Wei Huang, Selena Song, Haoyu Zhang, Qian Niu, Yusuke Iwasawa, Yutaka Matsuo, Jiaxian Guo
https://arxiv.org/abs/2502.18273 https://mastoxiv.page/@arXiv_csCL_bot/114069031700102129
- Benchmarking NLP-supported Language Sample Analysis for Swiss Children's Speech
Anja Ryser, Yingqiang Gao, Sarah Ebling
https://arxiv.org/abs/2504.00780 https://mastoxiv.page/@arXiv_csCL_bot/114267149909002069
- Cultural Biases of Large Language Models and Humans in Historical Interpretation
Fabio Celli, Georgios Spathulas
https://arxiv.org/abs/2504.02572 https://mastoxiv.page/@arXiv_csCL_bot/114278467094094490
- BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text
Jiageng Wu, et al.
https://arxiv.org/abs/2504.19467 https://mastoxiv.page/@arXiv_csCL_bot/114420036189999973
- Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potentia...
Yiming Huang, Biquan Bie, Zuqiu Na, Weilin Ruan, Songxin Lei, Yutao Yue, Xinlei He
https://arxiv.org/abs/2505.15392 https://mastoxiv.page/@arXiv_csCL_bot/114550277171100272
- Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods
Raza, Qureshi, Farooq, Lotif, Chadha, Pandya, Emmanouilidis
https://arxiv.org/abs/2505.17870 https://mastoxiv.page/@arXiv_csCL_bot/114572956853819813
- LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
Fu, Jiang, Hong, Li, Guo, Yang, Chen, Zhang
https://arxiv.org/abs/2506.14493 https://mastoxiv.page/@arXiv_csCL_bot/114703502552989170
- GHTM: A Graph-based Hybrid Topic Modeling Approach with a Benchmark Dataset for the Low-Resource ...
Farhana Haque, Md. Abdur Rahman, Sumon Ahmed
https://arxiv.org/abs/2508.00605 https://mastoxiv.page/@arXiv_csCL_bot/114969875643478303
- Link Prediction for Event Logs in the Process Industry
Anastasia Zhukova, Thomas Walton, Christian E. Lobm\"uller, Bela Gipp
https://arxiv.org/abs/2508.09096 https://mastoxiv.page/@arXiv_csCL_bot/115020938764936882
- AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
Huang, Cao, Zhang, Kang, Wang, Wang, Luo, Zheng, Qian, Chen, Yu
https://arxiv.org/abs/2509.16952 https://mastoxiv.page/@arXiv_csCL_bot/115253526588472475
- Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortio...
Jun Seo Kim, Hyemi Kim, Woo Joo Oh, Hongjin Cho, Hochul Lee, Hye Hyeon Kim
https://arxiv.org/abs/2509.17292 https://mastoxiv.page/@arXiv_csCL_bot/115253586227941157
- Dual-Space Smoothness for Robust and Balanced LLM Unlearning
Han Yan, Zheyuan Liu, Meng Jiang
https://arxiv.org/abs/2509.23362 https://mastoxiv.page/@arXiv_csCL_bot/115293308293558024
- The Rise of AfricaNLP: Contributions, Contributors, Community Impact, and Bibliometric Analysis
Tadesse Destaw Belay, et al.
https://arxiv.org/abs/2509.25477 https://mastoxiv.page/@arXiv_csCL_bot/115298213432594791
- Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Reco...
Srivastav, Zheng, Bezzam, Le Bihan, Koluguri, \.Zelasko, Majumdar, Moumen, Gandhi
https://arxiv.org/abs/2510.06961 https://mastoxiv.page/@arXiv_csCL_bot/115343748052193267
- Neuron-Level Analysis of Cultural Understanding in Large Language Models
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka
https://arxiv.org/abs/2510.08284 https://mastoxiv.page/@arXiv_csCL_bot/115349533441895984
- CLMN: Concept based Language Models via Neural Symbolic Reasoning
Yibo Yang
https://arxiv.org/abs/2510.10063 https://mastoxiv.page/@arXiv_csCL_bot/115372392366793754
- Schema for In-Context Learning
Chen, Chen, Wang, Leong, Fung, Bernales, Aspuru-Guzik
https://arxiv.org/abs/2510.13905 https://mastoxiv.page/@arXiv_csCL_bot/115389057899856601
- Evaluating Latent Knowledge of Public Tabular Datasets in Large Language Models
Matteo Silvestri, Fabiano Veglianti, Flavio Giorgi, Fabrizio Silvestri, Gabriele Tolomei
https://arxiv.org/abs/2510.20351 https://mastoxiv.page/@arXiv_csCL_bot/115428615784704418
- LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data
Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot
https://arxiv.org/abs/2510.24434 https://mastoxiv.page/@arXiv_csCL_bot/115457025096322944
- Surfacing Subtle Stereotypes: A Multilingual, Debate-Oriented Evaluation of Modern LLMs
Muhammed Saeed, Muhammad Abdul-mageed, Shady Shehata
https://arxiv.org/abs/2511.01187 https://mastoxiv.page/@arXiv_csCL_bot/115491321130591723
toXiv_bot_toot
@arXiv_csLG_bot@mastoxiv.page2026-02-25 10:44:51
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi
https://arxiv.org/abs/2602.21189 https://arxiv.org/pdf/2602.21189 https://arxiv.org/html/2602.21189
arXiv:2602.21189v1 Announce Type: new
Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines success if any of $k$ independently sampled solutions passes a verifier. This multi-sample inference metric has motivated inference-aware fine-tuning methods that directly optimize pass@$k$. However, prior work reports a recurring trade-off: pass@k improves while pass@1 degrades under such methods. This trade-off is practically important because pass@1 often remains a hard operational constraint due to latency and cost budgets, imperfect verifier coverage, and the need for a reliable single-shot fallback. We study the origin of this trade-off and provide a theoretical characterization of when pass@k policy optimization can reduce pass@1 through gradient conflict induced by prompt interference. We show that pass@$k$ policy gradients can conflict with pass@1 gradients because pass@$k$ optimization implicitly reweights prompts toward low-success prompts; when these prompts are what we term negatively interfering, their upweighting can rotate the pass@k update direction away from the pass@1 direction. We illustrate our theoretical findings with large language model experiments on verifiable mathematical reasoning tasks.
toXiv_bot_toot
@Techmeme@techhub.social2026-02-19 16:22:04
Google rolls out Gemini 3.1 Pro, which it says is "a step forward in core reasoning", for AI Pro and Ultra subscribers; the .1 increment is a first for Google (Abner Li/9to5Google)
https://9to5google.com/2026/02/19/google-announces-gem…
