Inspired by the dual-process theory of human cognition from Thinking, Fast and Slow, we introduce PRIME (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates System 1 (fast, intuitive thinking) and System 2 (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for planning, hypothesis generation, retrieval, information integration, and decision-making. This multi-agent design mimics human cognitive processes faithfully and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.

, which leverages information retrieval specifically for generated sub-questions and re-answers these sub-questions with the relevant contextual information. Additionally, a Retrieval-Augmented Factuality Scorer is proposed to replace the original discriminator, prioritizing reasoning paths that meet high standards of factuality. Experimental results with LLaMA 3.1 show that RARE enables open-source LLMs to achieve competitive performance with top closed-source models like GPT-4 and GPT-4o. This research establishes RARE as a scalable solution for improving LLMs in domains where logical coherence and factual integrity are critical.

As social robots get more deeply integrated into our everyday lives, they will be expected to engage in meaningful conversations and exhibit socio-emotionally intelligent listening behaviors when interacting with people. Active listening and backchanneling could be one way to enhance robots’ communicative capabilities and enhance their effectiveness in eliciting deeper self-disclosure, providing a sense of empathy, and forming positive rapport and relationships with people. Thus, we developed an LLM-powered social robot that can exhibit contextually appropriate sentiment-based backchanneling and active listening behaviors (active listening+backchanneling) and compared its efficacy in eliciting people’s self-disclosure in comparison to robots that do not exhibit any of these listening behaviors (control) and a robot that only exhibits backchanneling behavior (backchanneling-only). Through our experimental study with sixty-five participants, we found the participants who conversed with the active listening robot perceived the interactions more positively, in which they exhibited the highest self-disclosures, and reported the strongest sense of being listened to. The results of our study suggest that the implementation of active listening behaviors in social robots has the potential to improve human-robot communication and could further contribute to the building of deeper human-robot relationships and rapport.

OBJECTIVES: To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. MATERIALS AND METHODS: We created the BioInstruct, comprising 25 005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. RESULTS AND DISCUSSION: Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. CONCLUSION: The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.

It is common to listen to songs that match one's mood. Thus, an AI music recommendation system that is aware of the user's emotions is likely to provide a superior user experience to one that is unaware. In this paper, we present an emotion-aware music recommendation system. Multiple models are discussed and evaluated for affect identification from a live image of the user. We propose two models: DRViT, which applies dynamic routing to vision transformers, and InvNet50, which uses involution. All considered models are trained and evaluated on the AffectNet dataset. Each model outputs the user's estimated valence and arousal under the circumplex model of affect. These values are compared to the valence and arousal values for songs in a Spotify dataset, and the top-five closest-matching songs are presented to the user. Experimental results of the models and user testing are presented.

Long Phan, Tai Dang, Hieu Tran, Trieu H. Trinh, Vy Phan, Lam D. Chau, Minh-Thang Luong. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

The main agricultural crop in Vietnam is rice. After crop harvesting, the residue is burned by the farmers in the south and north of Vietnam to prepare for the next crop. In this paper, we have analyzed satellite and ground data to study the influence of crop residue burning on aerosol parameters and air quality. Our results show pronounced changes in aerosol properties and air quality, which have adverse impacts on human health and long-term impacts on climate.

As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings. The BigScience workshop, a 1-year international and multidisciplinary initiative, was formed with the goal of researching and training large language models as a values-driven undertaking, putting issues of ethics, harm, and governance in the foreground. This paper documents the data creation and curation efforts undertaken by BigScience to assemble the Responsible Open-science Open-collaboration Text Sources (ROOTS) corpus, a 1.6TB dataset spanning 59 languages that was used to train the 176-billion-parameter BigScience Large Open-science Open-access Multilingual (BLOOM) language model. We further release a large initial subset of the corpus and analyses thereof, and hope to empower large-scale monolingual and multilingual modeling projects with both the data and the processing tools, as well as stimulate research around this large multilingual corpus.

In this paper, we consider the IoT data discovery problem in very large and growing scale networks. Specifically, we investigate in depth the routing table summarization techniques to support effective and space-efficient IoT data discovery routing. Novel summarization algorithms, including alphabetical based, hash based, and meaning based summarization and their corresponding coding schemes are proposed. The issue of potentially misleading routing due to summarization is also investigated. Subsequently, we analyze the strategy of when to summarize in order to balance the tradeoff between the routing table compression rate and the chance of causing misleading routing. For experimental study, we have collected 100K IoT data streams from various IoT databases as the input dataset. Experimental results show that our summarization solution can reduce the routing table size by 20 to 30 folds with 2-5% increase in latency when compared with similar peer-to-peer discovery routing algorithms without summarization. Also, our approach outperforms DHT based approaches by 2 to 6 folds in terms of latency and traffic.

Prior research exploited the repetitiveness of code changes to enable several tasks such as code completion, bug-fix recommendation, library adaption, etc. These and other novel applications require accurate detection of semantic changes, but the state-of-the-art methods are limited to algorithms that detect specific kinds of changes at the syntactic level. Existing algorithms relying on syntactic similarity have lower accuracy, and cannot effectively detect semantic change patterns. We introduce a novel graph-based mining approach, CPatMiner, to detect previously unknown repetitive changes in the wild, by mining fine-grained semantic code change patterns from a large number of repositories. To overcome unique challenges such as detecting meaningful change patterns and scaling to large repositories, we rely on fine-grained change graphs to capture program dependencies. We evaluate CPatMiner by mining change patterns in a diverse corpus of 5,000+ open-source projects from GitHub across a population of 170,000+ developers. We use three complementary methods. First, we sent the mined patterns to 108 open-source developers. We found that 70% of respondents recognized those patterns as their meaningful frequent changes. Moreover, 79% of respondents even named the patterns, and 44% wanted future IDEs to automate such repetitive changes. We found that the mined change patterns belong to various development activities: adaptive (9%), perfective (20%), corrective (35%) and preventive (36%, including refactorings). Second, we compared our tool with the state-of-the-art, AST-based technique, and reported that it detects 2.1x more meaningful patterns. Third, we use CPatMiner to search for patterns in a corpus of 88 GitHub projects with longer histories consisting of 164M SLOCs. It constructed 322K fine-grained change graphs containing 3M nodes, and detected 17K instances of change patterns from which we provide unique insights on the practice of change patterns among individuals and teams. We found that a large percentage (75%) of the change patterns from individual developers are commonly shared with others, and this holds true for teams. Moreover, we found that the patterns are not intermittent but spread widely over time. Thus, we call for a community-based change pattern database to provide important resources in novel applications.

To avoid the exposure of original source code in a Web application, the variable names in JS code deployed in the wild are often replaced by short, meaningless names, thus making the code extremely difficult to manually understand and analysis. This paper presents JSNeat, an information retrieval (IR)-based approach to recover the variable names in minified JS code. JSNeat follows a data-driven approach to recover names by searching for them in a large corpus of open-source JS code. We use three types of contexts to match a variable in given minified code against the corpus including the context of the properties and roles of the variable, the context of that variable and relations with other variables under recovery, and the context of the task of the function to which the variable contributes. We performed several empirical experiments to evaluate JSNeat on the dataset of more than 322K JS files with 1M functions, and 3.5M variables with 176K unique variable names. We found that JSNeat achieves a high accuracy of 69.1%, which is the relative improvements of 66.1% and 43% over two state-of-the-art approaches JSNice and JSNaughty, respectively. The time to recover for a file or a variable with JSNeat is twice as fast as with JSNice and 4x as fast as with JNaughty, respectively.

Statistical machine translation (SMT) is a fast-growing sub-field of computational linguistics. Until now, the most popular automatic metric to measure the quality of SMT is BiLingual Evaluation Understudy (BLEU) score. Lately, SMT along with the BLEU metric has been applied to a Software Engineering task named code migration. (In) Validating the use of BLEU score could advance the research and development of SMT-based code migration tools. Unfortunately, there is no study to approve or disapprove the use of BLEU score for source code. In this paper, we conducted an empirical study on BLEU score to (in) validate its suitability for the code migration task due to its inability to reflect the semantics of source code. In our work, we use human judgment as the ground truth to measure the semantic correctness of the migrated code. Our empirical study demonstrates that BLEU does not reflect translation quality due to its weak correlation with the semantic correctness of translated code. We provided counter-examples to show that BLEU is ineffective in comparing the translation quality between SMT-based models. Due to BLEU's ineffectiveness for code migration task, we propose an alternative metric RUBY, which considers lexical, syntactical, and semantic representations of source code. We verified that RUBY achieves a higher correlation coefficient with the semantic correctness of migrated code, 0.775 in comparison with 0.583 of BLEU score. We also confirmed the effectiveness of RUBY in reflecting the changes in translation quality of SMT-based translation models. With its advantages, RUBY can be used to evaluate SMT-based code migration models.

Unexpected interactions among features induce most bugs in a configurable software system. Exhaustively analyzing all the exponential number of possible configurations is prohibitively costly. Thus, various sampling techniques have been proposed to systematically narrow down the exponential number of legal configurations to be analyzed. Since analyzing all selected configurations can require a huge amount of effort, fault-based configuration prioritization, that helps detect faults earlier, can yield practical benefits in quality assurance. In this paper, we propose CoPro, a novel formulation of feature-interaction bugs via common program entities enabled/disabled by the features. Leveraging from that, we develop an efficient feature-interaction-aware configuration prioritization technique for a configurable system by ranking the configurations according to their total number of potential bugs. We conducted several experiments to evaluate CoPro on the ability to detect configuration-related bugs in a public benchmark. We found that CoPro outperforms the state-of-the-art configuration prioritization techniques when we add them on advanced sampling algorithms. In 78% of the cases, CoPro ranks the buggy configurations at the top 3 positions in the resulting list. Interestingly, CoPro is able to detect 17 not-yet-discovered feature-interaction bugs.