Misha Khalman

Misha Khalman has 2 papers in our library, in 2023; often with Mohammad Saleh, Peter J. Liu, Rishabh Joshi.

2 papers in our library · 2023

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).

SLiC-HF: Sequence Likelihood Calibration with Human Feedback (2023 · 135 citations)
The paper looks for a lighter alternative to RLHF with PPO for aligning language models with human preferences.
Statistical Rejection Sampling Improves Preference Optimization (2023 · 101 citations)
The paper addresses a statistical gap in offline alignment methods. DPO and SLiC learn from preference pairs, but those pairs come from human-annotated data or the SFT policy, not from the optimal policy being estimated. As a result, their fitting is not a proper maximum-likelihood estimate. The authors propose…

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

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

Papers of our library cite their works 3,598 times (of the 141,840 papers whose bibliographies we read); 235 citing papers with a page here →.

Updated 24 October 2026