ML Newsnew | past | best | rss | submit about
Stories from August 16, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. It's How You Ask: Gender-Associated Linguistic Bias in LLMs (arxiv.org)
22 points by sbulaev 50 days ago | hide | past | pdf | 10 comments
2. Inducing LLM to assert own consciousness restores human beliefs and values (arxiv.org)
5 points by yboris 49 days ago | hide | past | pdf | 1 comment
3. RL for LLM Reasoning Is Sparse Policy Selection, Not Capability Learning (arxiv.org)
3 points by BlackGlory 49 days ago | hide | past | pdf | discuss
4. OEIS Open: A benchmark of 492 unsolved math conjectures, formalized in Lean (arxiv.org)
2 points by tadamcz 49 days ago | hide | past | pdf | discuss
5. Vero: Can AI Agents Build Formally Verified Software Repositories? (arxiv.org)
2 points by ninadwrites 49 days ago | hide | past | pdf | discuss
6. Invisible to the Machine: auditing AI recommendation against a complete census (arxiv.org)
2 points by fspunch 49 days ago | hide | past | pdf | discuss
7. Does Fixing Break Security? An Empirical Study of LLM Security Degradation (arxiv.org)
1 point by Jimmc414 49 days ago | hide | past | pdf | discuss
8. Why Do Prefetchers Fail? Let Agents Answer (arxiv.org)
1 point by Jimmc414 49 days ago | hide | past | pdf | discuss
9. A Generative Cramér-Rao Bound (arxiv.org)
1 point by hasley 49 days ago | hide | past | pdf | 1 comment
About | RSS | RSS (all) | HN arXiv