paper-with-me

Papers

Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction

2026-01-21 · Junjie An, Jingguang Tian, Tianyi Wang, Yu Gao, Xiaofeng Mou, Yi Xu arxiv

End-to-end automatic speech recognition (ASR) systems frequently misrecognize domain-specific phrases like named entities, which can cause catastrophic failures in downstream tasks. A new family of named entity correction methods based on large language models (LLMs) has recently emerged. However, these approaches have yet to fully exploit the sophisticated reasoning capabilities inherent to LLMs. To bridge this gap, we propose a novel retrieval-augmented generation framework for correcting named entity errors in ASR. Our approach consists of two key components: (1) a rephrasing language model (RLM) for named entity recognition, followed by candidate retrieval using a phonetic-level edit distance; and (2) a novel self-taught reasoning model with adaptive chain-of-thought (A-STAR) that dynamically adjusts the depth of its reasoning based on task difficulty. Experiments on the AISHELL-1 and Homophone datasets demonstrate the effectiveness of our method, which achieves relative reductions in the named entity character error rate of 17.96\% and 34.42\%, respectively, compared to a strong baseline.

📄 PDF Abstract BibTeX arXiv:2602.12287

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Results from the Paper

RankTaskDatasetModelMetrics
#19 Speech Recognition AISHELL-1 Retrieval-Augmented Self-Taught Reasonin Word Error Rate (WER): 17.96

Similar Papers 제목 키워드 기반

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

2025-05-22 · Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee 외

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often…

Diversity

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

2024-06-27 · Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao 외

This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-…

Question AnsweringRAGRetrievalRetrieval-augmented Generation

STaR-SQL: Self-Taught Reasoner for Text-to-SQL

2025-02-19 · Mingqian He, Yongliang Shen, Wenqi Zhang, Qiuying Peng 외

Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as…

Text to SQLText-To-SQL

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

2023-10-17 · Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil 외

Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Gen…

Fact VerificationQuestion AnsweringRAGResponse Generation+2

Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used

2026-02-06 · Srijan Shakya, Anamaria-Roberta Hartl, Sepp Hochreiter, Korbinian Pöppel arxiv

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a…