Cost-aware abstention cuts wrong routes on IT ticket classification
On 47,837 tickets, a calibration-selected TF-IDF policy cuts test cost 38.1% and wrong routes from 15.3% to 3.5%.
Stories per day · 30 days
10 stories, newest first · one card per story
Stories tagged #abstention
Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection
A learned answer selector on Qwen3-14B improves TriviaQA coverage and lowers scored-answer errors versus confidence filtering.
A Developer’s Guide to Laya: Zero-Shot Decisions and Calibration
A coding guide shows how to use Laya for zero-shot decisions, calibration, and abstention on CLINC150.
Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention
RegimeAbstain uses structural retrieval features to abstain on predictable multi-hop failures, cutting confident wrong answers.
Available Guardrails: Certifying Selective Prediction across ML Systems
Finite data often blocks certifying selective-prediction safety gates, and split planning recovers part of the lost coverage.
An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency
A zero-parameter Memory Decision Layer cuts LLM hallucination from conflicting retrieved memories by about 56 percent.
Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
Gating softmax attention supplies abstention and noise filtering, with filtering gains growing from 10M to 350M models.
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
Chain-of-Self-Questioning prompting cuts LLM wrong-answer commitments 32% relative while raising answered accuracy, holding across eleven model families.
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
Paper proposes a competence gate pooling language model forecasts with external priors, improving Brier score from 0.0771 to 0.0732 across 2,357 binary questions.
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
A linear hidden-state direction encodes question impossibility in 1.7B-70B LLMs, but misalignment with the safety-refusal pathway explains why models answer unanswerable questions.