Structured decisions by year¶
简体中文 · English
Papers are newest first by arXiv v1. Jev is a continually updated hosted product and appears separately, without an invented paper date.
2026¶
- 2026-10-21 — When Multiple Choices Are Correct: Distinguish normalized categorical shares from independently queried binary correctness probabilities; the former are not calibrated binary confidence. The paper studies Jev, Luna and Gemini. Bounded component only; full experiments are not reproduced.
- 2026-10-20 — Multimodal Reranking Is a System One Decision: Instead of generating a ranked list or training a separate pointwise reranker, the model scores each candidate by reading the probability of its letter label at the first answer position. The readout follows setwise and FIRST-style methods; the paper tests how this approach works zero-shot on images and visual documents, and whether text-only decision tuning transfers to visual reranking. Bounded component only; full experiments are not reproduced.
- 2026-10-16 — Jev-as-a-Judge for Brazilian Portuguese Information Retrieval: Relevance Assessment and Reranking: On Quati it separately uses an independent Noul probability that each document directly answers the query, gathers every batch, and sorts the results. Candidates do not compete in a single Choice, probabilities are not mixed with BM25 scores, and there is no trained calibrator. Evaluation protocol interface; not a model capability result.
- 2026-10-15 — Prism-1: A softmax combines independent scores. Softmax alone cannot guarantee this without attention isolation and position reset. Bounded component only; full experiments are not reproduced.
- 2026-01-19 — Calibration-Aware Reinforcement Learning: The paper adjusts decision-token probabilities directly to reduce ECE without sacrificing accuracy. The repository reports accuracy alongside Brier score and ECE, fits temperature only on validation, and forbids test-set tuning.
2025¶
- 2025-08-11 — GLiClass: This avoids unstable parsing of generative LLM outputs and separate cross-encoder inference on each text–label pair. The repository retains the defining mechanisms: candidate content affects scores, and one normalization produces a distribution over all candidates.
- 2025-07-22 — RLCR: RLCR predicts both an answer and its confidence and adds a bounded proper scoring rule so honest probabilities maximize expected reward. The local baseline minimizes multiclass Brier over the full candidate distribution.