Yong Lin

Yong Lin has 2 papers in our library, in 2024, most of them on Language models & pretraining; often with Haoxiang Wang, Shizhe Diao, Wei Xiong.

2 papers in our library · 2024

The profile is the library's match of the name; two people with one name are not always told apart.

Affiliations

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

Of its works in our library: the number of works on each and its rating among them.

The most cited first (OpenAlex and our library).

Mitigating the Alignment Tax of RLHF (2024 · 82 citations)
RLHF makes LLMs follow human preferences, but it also tends to erode skills learned in pre-training. This loss is called the alignment tax. The authors measured it by aligning OpenLLaMA-3B on the Anthropic helpfulness/harmlessness data with Rejection Sampling Fine-tuning (RSF) and DPO. They then tracked performance…
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024 · 66 citations)
Standard RLHF compresses human judgments into one scalar reward. This pushes a model toward an "average user" and ignores people whose tastes conflict, such as those who want useful but short answers. The authors propose Directional Preference Alignment (DPA) to address this.

10 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 113 times (of the 141,840 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated 24 October 2026