20 results for “error correction”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper investigates how social chatbots can recover from mistakes and maintain user trust.
Jungyeul Park, Kyungtae Lim, Wonjun Oh, Benjamin Nguyen +3 more
This paper refines word-based grammatical error annotation for L2 Korean by adapting existing resources to better reflect Korean morphology and error types, improving the evaluation of Korean Grammati…
This paper proposes iterative cross-layer semantic error correction (ICL-SEC) framework for closing the loop between physical-layer decoder and application-level language model, using a Confirm prior-…
This paper presents a product coding scheme that converts bit-level reliability into block-level reliability, achieving the same asymptotic rate.
Develops an equational theory for Detector Error Models (DEMs) in quantum circuits and provides a sound decision procedure for DEM equivalence.
The paper introduces SB-ECC, a novel score-based decoder that models error correction as continuous-time denoising, achieving state-of-the-art performance across various code families and noise levels…
This paper systematically studies how soft errors propagate during Large Language Model (LLM) inference using a novel fault-injection framework, providing critical insights and mitigation strategies f…
This paper proposes DeMix, a novel framework for simultaneously diagnosing erroneous samples and their error types in machine learning models.
Elad Sharony, Ido Greenberg, Jialin Song, Shie Mannor +2 more
CodeTriage, a learned policy, prioritizes edits before generating and testing revised code to improve efficiency in large language model code-repair systems.
Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei, Ziwei Dong +2 more
The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…
CB-SLICE is a novel concept-based method for discovering model error slices that leverages Concept Bottleneck Models (CBMs) to provide fine-grained, faithful explanations directly linked to the root c…
This paper introduces Voice Memory, an inference-only scheme for agentic speech recognition that uses a frozen corrector and a score-gated optimizer to improve speech recognition performance.
This paper proposes a method for selecting optimal error-correction codes (ECCs) for gain-cell embedded dynamic random-access memory (GCRAM) to minimize power consumption under a yield constraint.
This paper introduces burst t-deletion/insertion A-labeling codes to correct synchronization errors in DNA-based data storage.
Yuqing Yang, Qi Zhu, Zhen Han, Boran Han +4 more
This paper systematically evaluates tabular data referencing errors in large language models and presents methods to improve answer accuracy and detect errors.