Author

Lovedeep Gondara

British Columbia Cancer Agency, Simon Fraser university

h-index 20 Homepage View on Semantic Scholar

We have 3 of 126 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation

Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consistency can serve as a proxy for correctness when ground-truth labels are unavailable or expensive to obtain. In this paper, we test this assumpt...

Xiang Zhang, Lovedeep Gondara, Jekaterina Novikova · 0 citations

#artificial intelligence Preprint Oct 2026

The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express

When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or ablated. Holding the candidate pool, judge prompt, decoding and selection budget fixed, we score 15,406 UltraFeedback candidates under five formats with three judges, c...

Lovedeep Gondara, Jekaterina Novikova, S. Suresh et al. · 0 citations

#machine learning Jul 2026

A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

Stochastic Token Steering (STS), which gates each token independently with probability $p$, and Stochastic Block Steering (SBS), which gates a leading window once per sequence are introduced; neither requires a reward model or learned gating policy.

Nima Eshraghi, Lovedeep Gondara, Yuqing Huang et al. · arXiv.org · 0 citations