AI/ML News & Innovations Hub

AI/ML news, top picks, and generated innovation digests.

★ Visit ai-karthik.com
422Sources
13410News Items
8Top Picks
99Blogs
successLast Run

Latest AI/ML News

13410 matching items

Berkeley CHAI Score 40.0 USR-0023-nodate-research-aca-9cd64d81 Full article

Linear Probe Penalties Reduce LLM Sycophancy

Visiting ETH MsC student Henry Papadatos and supervising CHAI PhD student Rachel Freedman publish an article “Linear Probe Penalties Reduce LLM Sycophancy” at the NeurIPS SoLaR workshop. The paper demonstrates a generalizable methodology for reducing unwanted LLM behaviors that are not sufficiently disincentivized by RLHF fine-tuning

Berkeley CHAI Score 42.0 USR-0023-nodate-research-aca-c1c7e264 Full article

Getting By Goal Misgeneralization With a Little Help From a Mentor

“Tu Trinh, Ben Plaut, Khanh Nguyen, and Mohamad Danesh wrote the paper, “Getting By Goal Misgeneralization With a Little Help From a Mentor.” This paper explores whether goal misgeneralization can be mitigated by allowing an agent to ask for help when it is uncertain. The answer is mostly yes, although our current methods have substantial weaknesses and there are lots of interesting avenues for future work.”Tu Trinh, Ben Plaut, Khanh Nguyen, and Mohamad Danesh wrote the paper, This paper explores whether goal misgeneralization can be mitigated by allowing an agent to ask for help when it is uncertain. The answer is mostly yes, although our current methods have substantial weaknesses and there are lots of interesting avenues for future work.

Berkeley CHAI Score 37.0 USR-0023-nodate-research-aca-89569f1d Full article

Computational Frameworks for Human Care

Brian Christian, CHAI Affiliate, has published an article titled “ Computational Frameworks for Human Care ” in the most recent issue of Daedalus, the journal of the American Academy of Arts and Sciences. In it, Christian traces how AI alignment has progressed from simple reward mechanisms toward care-like relationships, revealing both the potential and limitations of machine caregiving while deepening our understanding of human care itself. The issue is titled “The Social Science of Caregiving” and was co-edited by CHAI Affiliate Alison Gopnik.

Berkeley CHAI Score 40.0 USR-0023-nodate-research-aca-346483e3 Full article

Learning to Coordinate with Experts

Khanh Nguyen, Benjamin Plaut, Tu Trinh, and Mohamad Danesh introduce a fundamental coordination problem called Learning to Yield and Request Control (YRC), where the objective is to learn a strategy that determines when to act autonomously and when to seek expert assistance. They build an open-source benchmark featuring diverse domains, propose a novel validation approach, and investigate the performance of various learning methods across diverse environments, yielding insights that can guide future research.