Analyzing the Role of Context in Forecasting with Large Language Models

This study evaluates the forecasting performance of recent language models (LLMs) on binary forecasting questions. We first introduce a novel dataset of over 600 binary forecasting questions, augmented with related news articles and their concise question-related summaries. We then explore the impact of input prompts with varying level of context on forecasting performance. The results indicate that incorporating news articles significantly improves performance, while using few-shot examples leads to a decline in accuracy. We find that larger models consistently outperform smaller models, highlighting the potential of LLMs in enhancing automated forecasting.

Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction

Predicting future events is an important activity with applications across multiple fields and domains. For example, the capacity to foresee stock market trends, natural disasters, business developments, or political events can facilitate early preventive measures and uncover new opportunities. Multiple diverse computational methods for attempting future predictions, including predictive analysis, time series forecasting, and simulations have been proposed. This study evaluates the performance of several large language models (LLMs) in supporting future prediction tasks, an under-explored domain. We assess the models across three scenarios: Affirmative vs. Likelihood questioning, Reasoning, and Counterfactual analysis. For this, we create a dataset1 by finding and categorizing news articles based on entity type and its popularity. We gather news articles before and after the LLMs training cutoff date in order to thoroughly test and compare model performance. Our research highlights LLMs potential and limitations in predictive modeling, providing a foundation for future improvements.

Using Large Language Models in Automatic Hint Ranking and Generation Tasks

The use of Large Language Models (LLMs) has increased significantly recently, with individuals frequently interacting with chatbots to receive answers to a wide range of questions. In an era where information is readily accessible, it is crucial to stimulate and preserve human cognitive abilities and maintain strong reasoning skills. This paper addresses such challenges by promoting the use of hints as an alternative or a supplement to direct answers. We first introduce a manually constructed hint dataset, WIKIHINT, which includes 5,000 hints created for 1,000 questions. We then finetune open-source LLMs such as LLaMA-3.1 for hint generation in answer-aware and answer-agnostic contexts. We assess the effectiveness of the hints with human participants who try to answer questions with and without the aid of hints. Additionally, we introduce a lightweight evaluation method, HINTRANK, to evaluate and rank hints in both answer-aware and answer-agnostic settings. Our findings show that (a) the dataset helps generate more effective hints, (b) including answer information along with questions generally improves hint quality, and (c) encoder-based models perform better than decoder-based models in hint ranking.

DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification

This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets.

Listen to the Patient: Enhancing Medical Dialogue Generation with Patient Hallucination Detection and Mitigation

Medical dialogue systems aim to provide medical services through patient-agent conversations. Previous methods typically regard patients as ideal users, focusing mainly on common challenges in dialogue systems, while neglecting the potential biases or misconceptions that might be introduced by real patients, who are typically non-experts. This study investigates the discrepancy between patients' expressions during medical consultations and their actual health conditions, defined as patient hallucination. Such phenomena often arise from patients' lack of knowledge and comprehension, concerns, and anxieties, resulting in the transmission of inaccurate or wrong information during consultations. To address this issue, we propose MedPH, a Medical dialogue generation method for mitigating the problem of Patient Hallucinations designed to detect and cope with hallucinations. MedPH incorporates a detection method that utilizes one-dimensional structural entropy over a temporal dialogue entity graph, and a mitigation strategy based on hallucination-related information to guide patients in expressing their actual conditions. Experimental results indicate the high effectiveness of MedPH when compared to existing approaches in both medical entity prediction and response generation tasks, while also demonstrating its effectiveness in mitigating hallucinations within interactive scenarios.

LLMTemporalComparator: A Tool for Analysing Differences in Temporal Adaptations of Large Language Models

This study addresses the challenges of analyzing temporal discrepancies in large language models (LLMs) trained on data from different time periods. To facilitate the automatic exploration of these differences, we propose a novel system that compares in a systematic way the outputs of two LLM versions based on user-defined queries. The system first generates a hierarchical topic structure rooted in a user-specified keyword, allowing for an organized comparison of topical categories. Subsequently, it evaluates the generated text by both LLMs to identify differences in vocabulary, information presentation, and underlying themes. This fully automated approach not only streamlines the identification of shifts in public opinion and cultural norms but also enhances our understanding of the adaptability and robustness of machine learning applications in response to temporal changes. By fostering research in continual model adaptation and comparative summarization, this work contributes to the development of more transparent machine learning models capable of capturing the nuances of evolving societal contexts.

Detecting Temporal Ambiguity in Questions

Detecting and answering ambiguous questions has been a challenging task in open-domain question answering. Ambiguous questions have different answers depending on their interpretation and can take diverse forms. Temporally ambiguous questions are one of the most common types of such questions. In this paper, we introduce TEMPAMBIQA, a manually annotated temporally ambiguous QA dataset consisting of 8,162 open-domain questions derived from existing datasets. Our annotations focus on capturing temporal ambiguity to study the task of detecting temporally ambiguous questions. We propose a novel approach by using diverse search strategies based on disambiguated versions of the questions. We also introduce and test non-search, competitive baselines for detecting temporal ambiguity using zero-shot and few-shot approaches.

Exploring Hint Generation Approaches in Open-Domain Question Answering

Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrieving relevant documents from a corpus like Wikipedia, whereas the latter uses generative models such as Large Language Models (LLMs) to generate the context. In this paper, we introduce a novel context preparation approach called HINTQA, which employs Automatic Hint Generation (HG) techniques. Unlike traditional methods, HINTQA prompts LLMs to produce hints about potential answers for the question rather than generating relevant context. We evaluate our approach across three QA datasets including TriviaQA, NaturalQuestions, and Web Questions, examining how the number and order of hints impact performance. Our findings show that the HINTQA surpasses both retrieval-based and generation-based approaches. We demonstrate that hints enhance the accuracy of answers more than retrieved and generated contexts.

Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval

Large language models (LLMs) have brought significant advancements to code generation and code repair, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, raises the risk of inadvertently propagating security vulnerabilities. Despite numerous studies investigating the safety of code LLMs, there remains a gap in comprehensively addressing their security features. In this work, we aim to present a comprehensive study aimed at precisely evaluating and enhancing the security aspects of code LLMs. To support our research, we introduce CodeSecEval, a meticulously curated dataset designed to address 44 critical vulnerability types with 180 distinct samples. CodeSecEval serves as the foundation for the automatic evaluation of code models in two crucial tasks: code generation and code repair, with a strong emphasis on security. Our experimental results reveal that current models frequently overlook security issues during both code generation and repair processes, resulting in the creation of vulnerable code. In response, we propose different strategies that leverage vulnerability-aware information and insecure code explanations to mitigate these security vulnerabilities. Furthermore, our findings highlight that certain vulnerability types particularly challenge model performance, influencing their effectiveness in real-world applications. Based on these findings, we believe our study will have a positive impact on the software engineering community, inspiring the development of improved methods for training and utilizing LLMs, thereby leading to safer and more trustworthy model deployment.

Is Your AI-Generated Code Really Secure? Evaluating Large Language Models on Secure Code Generation with CodeSecEval

Large language models (LLMs) have brought significant advancements to code generation and code repair, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, raises the risk of inadvertently propagating security vulnerabilities. Despite numerous studies investigating the safety of code LLMs, there remains a gap in comprehensively addressing their security features. In this work, we aim to present a comprehensive study aimed at precisely evaluating and enhancing the security aspects of code LLMs. To support our research, we introduce CodeSecEval, a meticulously curated dataset designed to address 44 critical vulnerability types with 180 distinct samples. CodeSecEval serves as the foundation for the automatic evaluation of code models in two crucial tasks: code generation and code repair, with a strong emphasis on security. Our experimental results reveal that current models frequently overlook security issues during both code generation and repair processes, resulting in the creation of vulnerable code. In response, we propose different strategies that leverage vulnerability-aware information and insecure code explanations to mitigate these security vulnerabilities. Furthermore, our findings highlight that certain vulnerability types particularly challenge model performance, influencing their effectiveness in real-world applications. Based on these findings, we believe our study will have a positive impact on the software engineering community, inspiring the development of improved methods for training and utilizing LLMs, thereby leading to safer and more trustworthy model deployment.