Extractive summarization involves selecting the most relevant sentences from a text. Recently, researchers have focused on advancing methods to improve state-of-the-art results in low-resource settings. Motivated by these advancements, we propose the MPoincareSum method. This method applies the Mamba state space model to generate the semantics of reviews and sentences, which are then concatenated. A Poincare compression is used to select the most meaningful features, followed by the application of a linear layer to predict sentence relevance based on the corresponding review. Finally, we paraphrase the relevant sentences to create the final summary. To evaluate the effectiveness of MPoincareSum, we conducted extensive experiments using the Amazon review dataset. The performance of the method was assessed using ROUGE scores. The experimental results demonstrate that MPoincareSum outperforms several existing approaches in the literature

Reference errors, such as citation and quotation errors, are common in scientific papers. Such errors can result in the propagation of inaccurate information, but are difficult and time-consuming to detect, posing a significant challenge to scientific publishing. To support automatic detection of reference errors, this work evaluated the ability of large language models in OpenAI's GPT family to detect quotation errors. Specifically, we prepared an expert-annotated, general-domain dataset of statement-reference pairs from journal articles. Large language models were evaluated in different settings with varying amounts of reference information provided by retrieval augmentation. Our results showed that large language models are able to detect erroneous citations with limited context and without fine-tuning. This study contributes to the growing literature that seeks to utilize artificial intelligence to assist in the writing, reviewing, and publishing of scientific papers. Potential avenues for further improvements in this task are also discussed.

Given that Large Language Models (LLMs) have made significant progress in writing code, can they now be used to autonomously reproduce results from research repositories? Such a capability would be a boon to the research community, helping researchers validate, understand, and extend prior work. To advance towards this goal, we introduce SUPER, the first benchmark designed to evaluate the capability of LLMs in setting up and executing tasks from research repositories. SUPERaims to capture the realistic challenges faced by researchers working with Machine Learning (ML) and Natural Language Processing (NLP) research repositories. Our benchmark comprises three distinct problem sets: 45 end-to-end problems with annotated expert solutions, 152 sub problems derived from the expert set that focus on specific challenges (e.g., configuring a trainer), and 602 automatically generated problems for larger-scale development. We introduce various evaluation measures to assess both task success and progress, utilizing gold solutions when available or approximations otherwise. We show that state-of-the-art approaches struggle to solve these problems with the best model (GPT-4o) solving only 16.3% of the end-to-end set, and 46.1% of the scenarios. This illustrates the challenge of this task, and suggests that SUPER can serve as a valuable resource for the community to make and measure progress.

Large Language Models (LLMs) can benefit from mitigating hallucinations through fact-checking and overcoming substantial computational overhead with parameter-efficient techniques such as Low-Rank Adaptation (LoRA). While some studies have explored the parallel integration of multiple LoRAs, these approaches need attention to the connections between them. This paper investigates methods to establish connections among multiple LoRAs. We create three reasoning datasets tailored to fact-checking and fine-tune individual LoRAs, allowing them to view and reason from diverse perspectives. Then, we explore strategies for allocating these reasoning LoRAs and introduce LoraMap, an approach to map connections between them. The results on the fact-checking task demonstrate that the performance of LoraMap is superior to LoraHub, an existing LoRA composition method. LoraMap also outperforms with significantly fewer parameters than LoraConcat, which concatenates LoRAs and further fine-tunes them.

Large language models (LLMs) exhibit an intriguing ability to learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL). Understandably, a swath of research has been dedicated to uncovering the theories underpinning ICL. One popular hypothesis explains ICL by task selection. LLMs identify the task based on the demonstration and generalize it to the prompt. Another popular hypothesis is that ICL is a form of meta-learning, i.e., the models learn a learning algorithm at pre-training time and apply it to the demonstration. Finally, a third hypothesis argues that LLMs use the demonstration to select a composition of tasks learned during pre-training to perform ICL. In this paper, we empirically explore these three hypotheses that explain LLMs' ability to learn in context with a suite of experiments derived from common text classification tasks. We invalidate the first two hypotheses with counterexamples and provide evidence in support of the last hypothesis. Our results suggest an LLM could learn a novel task in context via composing tasks learned during pre-training.

Despite the strong performance of large language models (LLMs) across a wide range of tasks, they still have reliability issues. Previous studies indicate that strong LLMs like GPT-4-turbo excel in evaluating the reliability of responses from LLMs, but face efficiency and local deployment issues. Thus, to enable weak LLMs to effectively assess the reliability of LLM responses, we propose a novel cross-query-comparison-based method called $\textit{Meta Ranking}$ (MR). Unlike previous few-shot methods that solely based on in-context learning capabilities in LLMs, MR assesses reliability by pairwisely ranking the target query-response pair with multiple reference query-response pairs. We found that MR is highly effective in error detection for LLM responses, where weak LLMs, such as Phi-2, could surpass strong baselines like GPT-3.5-turbo, requiring only five reference samples and significantly improving efficiency. We further demonstrate that MR can enhance strong LLMs' performance in two practical applications: model cascading and instruction tuning. In model cascading, we combine open- and closed-source LLMs to achieve performance comparable to GPT-4-turbo with lower costs. In instruction tuning, we use MR for iterative training data filtering, significantly reducing data processing time and enabling LLaMA-7B and Phi-2 to surpass Alpaca-13B with fewer training tokens. These results underscore the high potential of MR in both efficiency and effectiveness.

Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among large-scale structured knowledge, especially world knowledge that explicitly covers abundant factual information remains questionable. Addressing this gap, our research investigates whether LLMs can effectively store, recall, and reason with knowledge on a large scale comparable to latest knowledge bases (KBs) such as Wikidata. Specifically, we focus on three crucial aspects to study the viability: (1) the efficiency of LLMs with different sizes in memorizing the exact knowledge in the large-scale KB; (2) the flexibility of recalling the memorized knowledge in response to natural language queries; (3) the capability to infer new knowledge through reasoning. Our findings indicate that while LLMs hold promise as large-scale KBs capable of retrieving and responding with flexibility, enhancements in their reasoning capabilities are necessary to fully realize their potential.

Large-scale conversational assistants like Alexa, Siri, Cortana and Google Assistant process every utterance using multiple models for domain, intent and named entity recognition. Given the decoupled nature of model development and large traffic volumes, it is extremely difficult to identify utterances processed erroneously by such systems. We address this challenge to detect domain classification errors using offline Transformer models. We combine utterance encodings from a RoBERTa model with the Nbest hypothesis produced by the production system. We then fine-tune end-to-end in a multitask setting using a small dataset of humanannotated utterances with domain classification errors. We tested our approach for detecting misclassifications from one domain that accounts for <0.5% of the traffic in a large-scale conversational AI system. Our approach achieves an F1 score of 30% outperforming a bi- LSTM baseline by 16.9% and a standalone RoBERTa model by 4.8%. We improve this further by 2.2% to 32.2% by ensembling multiple models.