Code-switching (CS) speech refers to the phenomenon of mixing two or more
languages within the same sentence. Despite the recent advances in automatic
speech recognition (ASR), CS-ASR is still a challenging task ought to the
grammatical structure complexity of the phenomenon and the data scarcity of
specific training corpus. In this work, we propose to leverage large language
models (LLMs) and lists of hypotheses generated by an ASR to address the CS
problem. Specifically, we first employ multiple well-trained ASR models for
N-best hypotheses generation, with the aim of increasing the diverse and
informative elements in the set of hypotheses. Next, we utilize the LLMs to
learn the hypotheses-to-transcription (H2T) mapping by adding a trainable
low-rank adapter. Such a generative error correction (GER) method directly
predicts the accurate transcription according to its expert linguistic
knowledge and N-best hypotheses, resulting in a paradigm shift from the
traditional language model rescoring or error correction techniques.
Experimental evidence demonstrates that GER significantly enhances CS-ASR
accuracy, in terms of reduced mixed error rate (MER). Furthermore, LLMs show
remarkable data efficiency for H2T learning, providing a potential solution to
the data scarcity problem of CS-ASR in low-resource languages.

本文提出了一种利用大型语言模型和自动语音识别所生成的假设列表来解决语码转换的问题的方法，通过低秩适配器实现假设到转录的映射，并且实验证明该方法显著提高了语码转换自动语音识别的准确性，并且大型语言模型在数据效率方面表现出色，为低资源语言中语码转换自动语音识别的数据稀缺问题提供了潜在解决方案。

大语言模型用于代码转换语音识别的生成错误校正

Generative error correction for code-switching speech recognition using  large language models

Inductive reasoning is a core problem-solving capacity: humans can identify
underlying principles from a few examples, which can then be robustly
generalized to novel scenarios. Recent work has evaluated large language models
(LLMs) on inductive reasoning tasks by directly prompting them yielding "in
context learning." This can work well for straightforward inductive tasks, but
performs very poorly on more complex tasks such as the Abstraction and
Reasoning Corpus (ARC). In this work, we propose to improve the inductive
reasoning ability of LLMs by generating explicit hypotheses at multiple levels
of abstraction: we prompt the LLM to propose multiple abstract hypotheses about
the problem, in natural language, then implement the natural language
hypotheses as concrete Python programs. These programs can be directly verified
by running on the observed examples and generalized to novel inputs. Because of
the prohibitive cost of generation with state-of-the-art LLMs, we consider a
middle step to filter the set of hypotheses that will be implemented into
programs: we either ask the LLM to summarize into a smaller set of hypotheses,
or ask human annotators to select a subset of the hypotheses. We verify our
pipeline's effectiveness on the ARC visual inductive reasoning benchmark, its
variant 1D-ARC, and string transformation dataset SyGuS. On a random 40-problem
subset of ARC, our automated pipeline using LLM summaries achieves 27.5%
accuracy, significantly outperforming the direct prompting baseline (accuracy
of 12.5%). With the minimal human input of selecting from LLM-generated
candidates, the performance is boosted to 37.5%. (And we argue this is a lower
bound on the performance of our approach without filtering.) Our ablation
studies show that abstract hypothesis generation and concrete program
representations are both beneficial for LLMs to perform inductive reasoning
tasks.

通过产生多个抽象假设并将其转化为具体的 Python 程序，进而为大型语言模型提高归纳推理能力，并利用自动生成的摘要或人工筛选的候选集来过滤生成的程序，从而在归纳推理任务中实现更高的准确性。

假设搜索：利用语言模型进行归纳推理

Hypothesis Search: Inductive Reasoning with Language Models

Literature-Based Discovery (LBD) aims to discover new scientific knowledge by
mining papers and generating hypotheses. Standard LBD is limited to predicting
pairwise relations between discrete concepts (e.g., drug-disease links). LBD
also ignores critical contexts like experimental settings (e.g., a specific
patient population where a drug is evaluated) and background knowledge and
motivations that human scientists consider (e.g., to find a drug candidate
without specific side effects). We address these limitations with a novel
formulation of contextualized-LBD (C-LBD): generating scientific hypotheses in
natural language, while grounding them in a context that controls the
hypothesis search space. We present a new modeling framework using retrieval of
``inspirations'' from a heterogeneous network of citations and knowledge graph
relations, and create a new dataset derived from papers. In automated and human
evaluations, our models improve over baselines, including powerful large
language models (LLMs), but also reveal challenges on the road to building
machines that generate new scientific knowledge.

本研究提出了一种基于文献的发现方法即 Contextualized-LBD，可以通过自然语言生成科学假设，并通过对假设搜索空间的控制将其融合文献背景、知识图谱等环境上下文，从而能够更好的挖掘科学知识。实验表明，该模型超越了 LLMs 等基线模型，但在构建机器生成科学知识的道路上还有很大的挑战。