We investigate how low-quality AI advisors, lacking quality disclosures, can help spread text-based lies while seeming to help people detect lies. Participants in our experiment discern truth from lies by evaluating transcripts from a game show that mimicked deceptive social media exchanges on topics with objective truths. We find that when relying on low-quality advisors without disclosures, participants' truth-detection rates fall below their own abilities, which recovered once the AI's true effectiveness was revealed. Conversely, high-quality advisor enhances truth detection, regardless of disclosure. We discover that participants' expectations about AI capabilities contribute to their undue reliance on opaque, low-quality advisors.

Lexical-semantic resources (LSRs), such as online lexicons or wordnets, are fundamental for natural language processing applications. In many languages, however, such resources suffer from quality issues: incorrect entries, incompleteness, but also, the rarely addressed issue of bias towards the English language and Anglo-Saxon culture. Such bias manifests itself in the absence of concepts specific to the language or culture at hand, the presence of foreign (Anglo-Saxon) concepts, as well as in the lack of an explicit indication of untranslatability, also known as cross-lingual \emph{lexical gaps}, when a term has no equivalent in another language. This paper proposes a novel crowdsourcing methodology for reducing bias in LSRs. Crowd workers compare lexemes from two languages, focusing on domains rich in lexical diversity, such as kinship or food. Our LingoGap crowdsourcing tool facilitates comparisons through microtasks identifying equivalent terms, language-specific terms, and lexical gaps across languages. We validated our method by applying it to two case studies focused on food-related terminology: (1) English and Arabic, and (2) Standard Indonesian and Banjarese. These experiments identified 2,140 lexical gaps in the first case study and 951 in the second. The success of these experiments confirmed the usability of our method and tool for future large-scale lexicon enrichment tasks.

In-context learning can help Large Language Models (LLMs) to adapt new tasks without additional training. However, this performance heavily depends on the quality of the demonstrations, driving research into effective demonstration selection algorithms to optimize this process. These algorithms assist users in selecting the best $k$ input-label pairs (demonstration examples) based on a given test input, enabling LLMs to in-context learn the relationship between the provided examples and the test inputs. Despite all the proposed demonstration selection algorithms, their efficiency and effectiveness remain unclear. This lack of clarity make it difficult to apply these algorithms in real-world scenarios and poses challenges for future research aimed at developing improved methods. This paper revisits six proposed algorithms, evaluating them on five datasets from both efficiency and effectiveness perspectives. Our experiments reveal significant variations in algorithm performance across different tasks, with some methods struggling to outperform random selection in certain scenarios. We also find that increasing the number of demonstrations does not always lead to better performance, and that there are often trade-offs between accuracy and computational efficiency. Our code is available at https://github.com/Tizzzzy/Demonstration_Selection_Overview.

Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia and tackles key challenges such as open-domain coverage, knowledge intensity, free-form responses, and topic shifts. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling. We propose a unified framework to standardize various conversational RAG methods and conduct a comprehensive evaluation of these methods on CORAL, demonstrating substantial opportunities for improving existing approaches.

Large language models (LLMs) are essential in natural language processing but often struggle with inference speed and computational efficiency, limiting real-time deployment. The key-value (KV) cache mechanism reduces computational overhead in transformer models, but challenges in maintaining contextual understanding remain. In this paper, we propose BUZZ, a novel KV caching algorithm that leverages structured contextual information to minimize cache memory usage while enhancing inference speed. BUZZ employs a beehive-structured sparse cache, incorporating a sliding window to capture recent information and dynamically segmenting historical tokens into chunks to prioritize important tokens in local neighborhoods. We evaluate BUZZ on four real-world datasets: CNN/Daily Mail, XSUM, Wikitext, and 10-QA. Our results demonstrate that BUZZ (1) reduces cache memory usage by $\textbf{2.5}\times$ in LLM inference while maintaining over 99% accuracy in long-text summarization, and (2) surpasses state-of-the-art performance in multi-document question answering by $\textbf{7.69%}$ under the same memory limit, where full cache methods encounter out-of-memory issues. Additionally, BUZZ achieves significant inference speedup with a $\log{n}$ time complexity. The code is available at https://github.com/JunqiZhao888/buzz-llm.

This work takes a pedagogical lens to explore the implications of generative AI (GenAI) models and tools, such as ChatGPT and GitHub Copilot, in a semester-long 2nd-year undergraduate Software Engineering Team Project. Qualitative findings from survey (39 students) and interviews (eight students) provide insights into the students' views on the impact of GenAI use on their coding experience, learning, and self-efficacy. Our results address a particular gap in understanding the role and implications of GenAI on teamwork, team-efficacy, and team dynamics. The analysis of the learning aspects is distinguished by the application of learning and pedagogy informed lenses to discuss the data. We propose a preliminary design space for GenAI-based programming learning tools highlighting the importance of considering the roles that GenAI can play during the learning process, the varying support-ability patterns that can be applied to each role, and the importance of supporting transparency in GenAI for team members and students in addition to educators.

It has recently been demonstrated empirically that in-context learning emerges in transformers when certain distributional properties are present in the training data, but this ability can also diminish upon further training. We provide a new theoretical understanding of these phenomena by identifying simplified distributional properties that give rise to the emergence and eventual disappearance of in-context learning. We do so by first analyzing a simplified model that uses a gating mechanism to choose between an in-weight and an in-context predictor. Through a combination of a generalization error and regret analysis we identify conditions where in-context and in-weight learning emerge. These theoretical findings are then corroborated experimentally by comparing the behaviour of a full transformer on the simplified distributions to that of the stylized model, demonstrating aligned results. We then extend the study to a full large language model, showing how fine-tuning on various collections of natural language prompts can elicit similar in-context and in-weight learning behaviour.

As LLMs exhibit a high degree of human-like capability, increasing attention has been paid to role-playing research areas in which responses generated by LLMs are expected to mimic human replies. This has promoted the exploration of role-playing agents in various applications, such as chatbots that can engage in natural conversations with users and virtual assistants that can provide personalized support and guidance. The crucial factor in the role-playing task is the effective utilization of character memory, which stores characters' profiles, experiences, and historical dialogues. Retrieval Augmented Generation (RAG) technology is used to access the related memory to enhance the response generation of role-playing agents. Most existing studies retrieve related information based on the semantic similarity of memory to maintain characters' personalized traits, and few attempts have been made to incorporate the emotional factor in the retrieval argument generation (RAG) of LLMs. Inspired by the Mood-Dependent Memory theory, which indicates that people recall an event better if they somehow reinstate during recall the original emotion they experienced during learning, we propose a novel emotion-aware memory retrieval framework, termed Emotional RAG, which recalls the related memory with consideration of emotional state in role-playing agents. Specifically, we design two kinds of retrieval strategies, i.e., combination strategy and sequential strategy, to incorporate both memory semantic and emotional states during the retrieval process. Extensive experiments on three representative role-playing datasets demonstrate that our Emotional RAG framework outperforms the method without considering the emotional factor in maintaining the personalities of role-playing agents. This provides evidence to further reinforce the Mood-Dependent Memory theory in psychology.

Retrieval-augmented generation (RAG) is a promising approach to address the limitations of fixed knowledge in large language models (LLMs). However, current benchmarks for evaluating RAG systems suffer from two key deficiencies: (1) they fail to adequately measure LLMs' capability in handling long-context retrieval due to a lack of datasets that reflect the characteristics of retrieved documents, and (2) they lack a comprehensive evaluation method for assessing LLMs' ability to generate long-form responses that effectively exploits retrieved information. To address these shortcomings, we introduce the Long$^2$RAG benchmark and the Key Point Recall (KPR) metric. Long$^2$RAG comprises 280 questions spanning 10 domains and across 8 question categories, each associated with 5 retrieved documents with an average length of 2,444 words. KPR evaluates the extent to which LLMs incorporate key points extracted from the retrieved documents into their generated responses, providing a more nuanced assessment of their ability to exploit retrieved information.

A well structured collection of the various Quantum Cascade Laser (QCL) design and working properties data provides a platform to analyze and understand the relationships between these properties. By analyzing these relationships, we can gain insights into how different design features impact laser performance properties such as the working temperature. Most of these QCL properties are captured in scientific text. There is therefore need for efficient methodologies that can be utilized to extract QCL properties from text and generate a semantically enriched and interlinked platform where the properties can be analyzed to uncover hidden relations. There is also the need to maintain provenance and reference information on which these properties are based. Semantic Web technologies such as Ontologies and Knowledge Graphs have proven capability in providing interlinked data platforms for knowledge representation in various domains. In this paper, we propose an approach for generating a QCL properties Knowledge Graph (KG) from text for semantic enrichment of the properties. The approach is based on the QCL ontology and a Retrieval Augmented Generation (RAG) enabled information extraction pipeline based on GPT 4-Turbo language model. The properties of interest include: working temperature, laser design type, lasing frequency, laser optical power and the heterostructure. The experimental results demonstrate the feasibility and effectiveness of this approach for efficiently extracting QCL properties from unstructured text and generating a QCL properties Knowledge Graph, which has potential applications in semantic enrichment and analysis of QCL data.