Related papers: No Dataset Needed for Downstream Knowledge Benchma…

Probing techniques have shown promise in revealing how LLMs encode human-interpretable concepts, particularly when applied to curated datasets. However, the factors governing a dataset's suitability for effective probe training are not…

Retrieval-Augmented Generation has shown remarkable results to address Large Language Models' hallucinations, which usually uses a large external corpus to supplement knowledge to LLMs. However, with the development of LLMs, the internal…

Recent advances in the finetuning of large language models (LLMs) have significantly improved their performance on established benchmarks, emphasizing the need for increasingly difficult, synthetic data. A key step in this data generation…

Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Large language Models (LLMs) are highly sensitive to variations in prompt formulation, which can significantly impact their ability to generate accurate responses. In this paper, we introduce a new task, Prompt Sensitivity Prediction, and a…

In this paper we present a technique of NLP to tackle the problem of inference relation (NLI) between pairs of sentences in a target language of choice without a language-specific training dataset. We exploit a generic translation dataset,…

Retrieval-augmented generation (RAG) on specialized domain datasets has shown improved performance when large language models (LLMs) are fine-tuned for generating responses to user queries. In this study, we develop a cybersecurity…

Ensuring large language model (LLM) reliability requires distinguishing objective unsolvability (inherent contradictions) from subjective capability limitations (tasks exceeding model competence). Current LLMs often conflate these…

In spite of much recent research in the area, it is still unclear whether subject-area question-answering data is useful for machine reading comprehension (MRC) tasks. In this paper, we investigate this question. We collect a large-scale…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Existing analysis work in machine reading comprehension (MRC) is largely concerned with evaluating the capabilities of systems. However, the capabilities of datasets are not assessed for benchmarking language understanding precisely. We…

In this paper, we propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. In customer-facing chatbots, companies are dealing with large amounts of user…

Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text often suffer from 1) reliance on compute-heavy paraphrasing augmentation and 2) the reversal…

Domain-specific knowledge can significantly contribute to addressing a wide variety of vision tasks. However, the generation of such knowledge entails considerable human labor and time costs. This study investigates the potential of Large…

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions. One of the key approaches to do this has been through the use of knowledge tracing (KT)…

Survey researchers face two key challenges: the rising costs of probability samples and missing data (e.g., non-response or attrition), which can undermine inference and increase the use of convenience samples. Recent work explores using…

Most recent few-shot learning approaches are based on meta-learning with episodic training. However, prior studies encounter two crucial problems: (1) \textit{the presence of inductive bias}, and (2) \textit{the occurrence of catastrophic…