Large language models (LLMs) demonstrate remarkable capabilities but face challenges from hallucinations, which typically arise from insufficient knowledge or context. While instructing LLMs to acknowledge knowledge limitations by responding with “I don’t know” appears promising, we find that models consistently struggle with admitting knowledge gaps. This challenge may originate from current instruction datasets that emphasise answer generation over knowledge boundary awareness. To address this limitation, we introduce **U**ncertainty-and-**S**ensitivity-Aware Tuning **(US-Tuning)**, a novel two-stage approach for contextual question answering (QA). The first stage enhances LLMs’ ability to recognise their knowledge boundaries, while the second stage reinforces instruction adherence through carefully designed causal prompts. Our experimental results demonstrate that US-Tuning not only significantly reduces incorrect answers in contextual QA but also improves models’ faithfulness to their parametric knowledge, mitigating hallucinations in general QA tasks. Our fine-tuned Llama2-7B model achieves up to a 34.7% improvement in handling out-of-knowledge questions and outperforms GPT-4 by 4.2% in overall performance.

In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications. However, they are significantly different. In ICL, a set of demonstrations is provided at the inference time, but the LLM’s parameters are not updated. In IT, a set of demonstrations is used to adjust the parameters of the LLM during training, but no demonstrations are provided at the inference time. Although a growing body of literature has explored ICL and IT, studies on these topics have largely been conducted in isolation, leading to a disconnect between these two paradigms. In this work, we explore the relationship between ICL and IT by examining how the hidden states of LLMs change in these two paradigms. Through carefully designed experiments conducted with LLaMA-2 and LLaMA-2-Chat (7B and 13B), we find that ICL and IT converge in LLM hidden states despite their apparent differences in implementation. Specifically, ICL changes an LLM’s hidden states as if its accompanying demonstrations were used to instructionally tune the model. Furthermore, the convergence between ICL and IT is largely contingent upon several factors related to the demonstration. Overall, this work offers a unique perspective to explore the connection between ICL and IT and sheds light on understanding the behaviors of LLMs.

In the financial domain, conducting entity-level sentiment analysis is crucial for accurately assessing the sentiment directed toward a specific financial entity. To our knowledge, no publicly available dataset currently exists for this purpose. In this work, we introduce an entity-level sentiment classification dataset, called FinEntity, that annotates financial entity spans and their sentiment (positive, neutral, and negative) in financial news. We document the dataset construction process in the paper. Additionally, we benchmark several pre-trained models (BERT, FinBERT, etc.) and ChatGPT on entity-level sentiment classification. In a case study, we demonstrate the practical utility of using FinEntity in monitoring cryptocurrency markets. The data and code of FinEntity is available at https://github.com/yixuantt/FinEntity.

Multi-hop question answering (QA) requires a model to retrieve and integrate information from multiple passages to answer a question. Rapid progress has been made on multi-hop QA systems with regard to standard evaluation metrics, including EM and F1. However, by simply evaluating the correctness of the answers, it is unclear to what extent these systems have learned the ability to perform multi-hop reasoning. In this paper, we propose an additional sub-question evaluation for the multi-hop QA dataset HotpotQA, in order to shed some light on explaining the reasoning process of QA systems in answering complex questions. We adopt a neural decomposition model to generate sub-questions for a multi-hop question, followed by extracting the corresponding sub-answers. Contrary to our expectation, multiple state-of-the-art multi-hop QA models fail to answer a large portion of sub-questions, although the corresponding multi-hop questions are correctly answered. Our work takes a step forward towards building a more explainable multi-hop QA system.