A survey of table reasoning with large language models
Table reasoning aims to generate inference results based on the user requirement and the
provided table. Enhancing the table reasoning capability of the model can aid in obtaining …
provided table. Enhancing the table reasoning capability of the model can aid in obtaining …
Open-Ethical AI: Advancements in Open-Source Human-Centric Neural Language Models
S Sicari, JF Cevallos M, A Rizzardi… - ACM Computing …, 2024 - dl.acm.org
This survey summarises the most recent methods for building and assessing helpful, honest,
and harmless neural language models, considering small, medium, and large-size models …
and harmless neural language models, considering small, medium, and large-size models …
Navigate through enigmatic labyrinth a survey of chain of thought reasoning: Advances, frontiers and future
Abstract Reasoning, a fundamental cognitive process integral to human intelligence, has
garnered substantial interest within artificial intelligence. Notably, recent studies have …
garnered substantial interest within artificial intelligence. Notably, recent studies have …
TAT-LLM: A Specialized Language Model for Discrete Reasoning over Financial Tabular and Textual Data
In this work, we develop a specialized language model with strong discrete reasoning
capabilities to tackle question answering (QA) over hybrid tabular and textual data in …
capabilities to tackle question answering (QA) over hybrid tabular and textual data in …
Improving biomedical abstractive summarisation with knowledge aggregation from citation papers
C Tang, S Wang, T Goldsack, C Lin - arxiv preprint arxiv:2310.15684, 2023 - arxiv.org
Abstracts derived from biomedical literature possess distinct domain-specific characteristics,
including specialised writing styles and biomedical terminologies, which necessitate a deep …
including specialised writing styles and biomedical terminologies, which necessitate a deep …
Train and Constrain: Phonologically Informed Tongue Twister Generation from Topics and Paraphrases
Previous work in phonologically and phonetically grounded language generation has
mainly focused on domains such as puns and poetry. In this article, we present new work on …
mainly focused on domains such as puns and poetry. In this article, we present new work on …
From classification to clinical insights: Towards analyzing and reasoning about mobile and behavioral health data with large language models
Z Englhardt, C Ma, ME Morris, X Xu, CC Chang… - arxiv preprint arxiv …, 2023 - arxiv.org
Passively collected behavioral health data from ubiquitous sensors holds significant promise
to provide mental health professionals insights from patient's daily lives; however …
to provide mental health professionals insights from patient's daily lives; however …
[HTML][HTML] A cross-attention augmented model for event-triggered context-aware story generation
Despite recent advancements, existing story generation systems continue to encounter
difficulties in effectively incorporating contextual and event features, which greatly influence …
difficulties in effectively incorporating contextual and event features, which greatly influence …
Cadge: Context-aware dialogue generation enhanced with graph-structured knowledge aggregation
Commonsense knowledge is crucial to many natural language processing tasks. Existing
works usually incorporate graph knowledge with conventional graph neural networks …
works usually incorporate graph knowledge with conventional graph neural networks …
Mixed Distillation Helps Smaller Language Models Reason Better
L Chenglin, Q Chen, L Li, C Wang, F Tao… - Findings of the …, 2024 - aclanthology.org
As large language models (LLMs) have demonstrated impressive multiple step-by-step
reasoning capabilities in recent natural language processing (NLP) reasoning tasks, many …
reasoning capabilities in recent natural language processing (NLP) reasoning tasks, many …