Non-cognitive skills are crucial for personal and social life well-being, and such skill development can be supported by narrative-based (e.g., storytelling) technologies. While generative AI enables interactive and role-playing storytelling, little is known about how users engage with and perceive the use of AI in social life simulation for non-cognitive skills learning. Additionally, the benefits of AI mentorship on self-reflection awareness and ability in this context remain largely underexplored. To this end, we introduced Simulife++, an interactive platform enabled by a large language model (LLM). The system allows users to act as protagonists, creating stories with one or multiple AI-based characters in diverse social scenarios. In particular, we expanded the Human-AI interaction to a Human-AI-AI collaboration by including a Sage Agent, who acts as a bystander, providing users with some perspectives and guidance on their choices and conversations in terms of non-cognitive skills to promote reflection. In a within-subject user study, our quantitative results reveal that, when accompanied by Sage Agent, users exhibit significantly higher levels of reflection on motivation, self-perceptions, and resilience & coping, along with an enhanced experience of narrative transportation. Additionally, our qualitative findings suggest that Sage Agent plays a crucial role in promoting reflection on non-cognitive skills, enhancing social communication and decision-making performance, and improving overall user experience within Simulife++. Multiple supportive relationships between Sage Agent and users were also reported. We offer design implications for the application of generative AI in narrative solutions and the future potential of Sage Agent for non-cognitive skill development in broader social contexts.
Emotion AI is the ability of computers to understand human emotional states. Existing works have achieved promising progress, but two limitations remain to be solved: 1) Previous studies have been more focused on short sequential video emotion analysis while overlooking long sequential video. However, the emotions in short sequential videos only reflect instantaneous emotions, which may be deliberately guided or hidden. In contrast, long sequential videos can reveal authentic emotions; 2) Previous studies commonly utilize various signals such as facial, speech, and even sensitive biological signals (e.g., electrocardiogram). However, due to the increasing demand for privacy, developing Emotion AI without relying on sensitive signals is becoming important. To address the aforementioned limitations, in this paper, we construct a dataset for Emotion Analysis in Long-sequential and De-identity videos called EALD by collecting and processing the sequences of athletes' post-match interviews. In addition to providing annotations of the overall emotional state of each video, we also provide the Non-Facial Body Language (NFBL) annotations for each player. NFBL is an inner-driven emotional expression and can serve as an identity-free clue to understanding the emotional state. Moreover, we provide a simple but effective baseline for further research. More precisely, we evaluate the Multimodal Large Language Models (MLLMs) with de-identification signals (e.g., visual, speech, and NFBLs) to perform emotion analysis. Our experimental results demonstrate that: 1) MLLMs can achieve comparable, even better performance than the supervised single-modal models, even in a zero-shot scenario; 2) NFBL is an important cue in long sequential emotion analysis. EALD will be available on the open-source platform.
Ultrasound robots are increasingly used in medical diagnostics and early disease screening. However, current ultrasound robots lack the intelligence to understand human intentions and instructions, hindering autonomous ultrasound scanning. To solve this problem, we propose a novel Ultrasound Embodied Intelligence system that equips ultrasound robots with the large language model (LLM) and domain knowledge, thereby improving the efficiency of ultrasound robots. Specifically, we first design an ultrasound operation knowledge database to add expertise in ultrasound scanning to the LLM, enabling the LLM to perform precise motion planning. Furthermore, we devise a dynamic ultrasound scanning strategy based on a \textit{think-observe-execute} prompt engineering, allowing LLMs to dynamically adjust motion planning strategies during the scanning procedures. Extensive experiments demonstrate that our system significantly improves ultrasound scan efficiency and quality from verbal commands. This advancement in autonomous medical scanning technology contributes to non-invasive diagnostics and streamlined medical workflows.
Activity and parameter sparsity are two standard methods of making neural networks computationally more efficient. Event-based architectures such as spiking neural networks (SNNs) naturally exhibit activity sparsity, and many methods exist to sparsify their connectivity by pruning weights. While the effect of weight pruning on feed-forward SNNs has been previously studied for computer vision tasks, the effects of pruning for complex sequence tasks like language modeling are less well studied since SNNs have traditionally struggled to achieve meaningful performance on these tasks. Using a recently published SNN-like architecture that works well on small-scale language modeling, we study the effects of weight pruning when combined with activity sparsity. Specifically, we study the trade-off between the multiplicative efficiency gains the combination affords and its effect on task performance for language modeling. To dissect the effects of the two sparsities, we conduct a comparative analysis between densely activated models and sparsely activated event-based models across varying degrees of connectivity sparsity. We demonstrate that sparse activity and sparse connectivity complement each other without a proportional drop in task performance for an event-based neural network trained on the Penn Treebank and WikiText-2 language modeling datasets. Our results suggest sparsely connected event-based neural networks are promising candidates for effective and efficient sequence modeling.
Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. However, there is growing concern that some of this performance actually reflects dataset contamination, where data closely resembling benchmark questions leaks into the training data, instead of true reasoning ability. To investigate this claim rigorously, we commission Grade School Math 1000 (GSM1k). GSM1k is designed to mirror the style and complexity of the established GSM8k benchmark, the gold standard for measuring elementary mathematical reasoning. We ensure that the two benchmarks are comparable across important metrics such as human solve rates, number of steps in solution, answer magnitude, and more. When evaluating leading open- and closed-source LLMs on GSM1k, we observe accuracy drops of up to 8%, with several families of models showing evidence of systematic overfitting across almost all model sizes. Further analysis suggests a positive relationship (Spearman's r^2 = 0.36) between a model's probability of generating an example from GSM8k and its performance gap between GSM8k and GSM1k, suggesting that some models may have partially memorized GSM8k. Nevertheless, many models, especially those on the frontier, show minimal signs of overfitting, and all models broadly demonstrate generalization to novel math problems guaranteed to not be in their training data.
Learning never ends, and there is no age limit to grow yourself. However, the educational landscape may face challenges in effectively catering to students' inclusion and diverse learning needs. These students should have access to state-of-the-art methods for lecture delivery, online resources, and technology needs. However, with all the diverse learning sources, it becomes harder for students to comprehend a large amount of knowledge in a short period of time. Traditional assistive technologies and learning aids often lack the dynamic adaptability required for individualized education plans. Large Language Models (LLM) have been used in language translation, text summarization, and content generation applications. With rapid growth in AI over the past years, AI-powered chatbots and virtual assistants have been developed. This research aims to bridge this gap by introducing an innovative study buddy we will be calling the 'SAMCares'. The system leverages a Large Language Model (LLM) (in our case, LLaMa-2 70B as the base model) and Retriever-Augmented Generation (RAG) to offer real-time, context-aware, and adaptive educational support. The context of the model will be limited to the knowledge base of Sam Houston State University (SHSU) course notes. The LLM component enables a chat-like environment to interact with it to meet the unique learning requirements of each student. For this, we will build a custom web-based GUI. At the same time, RAG enhances real-time information retrieval and text generation, in turn providing more accurate and context-specific assistance. An option to upload additional study materials in the web GUI is added in case additional knowledge support is required. The system's efficacy will be evaluated through controlled trials and iterative feedback mechanisms.
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs often operate at high bitrates or within narrow domains such as speech and lack the semantic clues required for efficient language modelling. Addressing these challenges, we introduce SemantiCodec, a novel codec designed to compress audio into fewer than a hundred tokens per second across diverse audio types, including speech, general sound, and music, without compromising quality. SemantiCodec features a dual-encoder architecture: a semantic encoder using a self-supervised pre-trained Audio Masked Autoencoder (AudioMAE), discretized using k-means clustering on extensive audio data, and an acoustic encoder to capture the remaining details. The semantic and acoustic encoder outputs are used to reconstruct audio via a diffusion-model-based decoder. SemantiCodec is presented in three variants with token rates of 25, 50, and 100 per second, supporting a range of ultra-low bit rates between 0.31 kbps and 1.40 kbps. Experimental results demonstrate that SemantiCodec significantly outperforms the state-of-the-art Descript codec on reconstruction quality. Our results also suggest that SemantiCodec contains significantly richer semantic information than all evaluated state-of-the-art audio codecs, even at significantly lower bitrates. Our code and demos are available at https://haoheliu.github.io/SemantiCodec/.
This paper introduces Aptly, a platform designed to democratize mobile app development, particularly for young learners. Aptly integrates a Large Language Model (LLM) with App Inventor, enabling users to create apps using their natural language. User's description is translated into a programming language that corresponds with App Inventor's visual blocks. A preliminary study with high school students demonstrated the usability and potential of the platform. Prior programming experience influenced how users interact with Aptly. Participants identified areas for improvement and expressed a shift in perspective regarding programming accessibility and AI's role in creative endeavors.
Graphical User Interfaces (GUIs) are central to app development projects. App developers may use the GUIs of other apps as a means of requirements refinement and rapid prototyping or as a source of inspiration for designing and improving their own apps. Recent research has thus suggested retrieving relevant GUI designs that match a certain text query from screenshot datasets acquired through crowdsourced or automated exploration of GUIs. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements, neglecting visual information such as icons or background images. In addition, retrieved screenshots are not steered by app developers and lack app features that require particular input data. To overcome these limitations, this paper proposes GUing, a GUI search engine based on a vision-language model called GUIClip, which we trained specifically for the problem of designing app GUIs. For this, we first collected from Google Play app introduction images which display the most representative screenshots and are often captioned (i.e.~labelled) by app vendors. Then, we developed an automated pipeline to classify, crop, and extract the captions from these images. This resulted in a large dataset which we share with this paper: including 303k app screenshots, out of which 135k have captions. We used this dataset to train a novel vision-language model, which is, to the best of our knowledge, the first of its kind for GUI retrieval. We evaluated our approach on various datasets from related work and in a manual experiment. The results demonstrate that our model outperforms previous approaches in text-to-GUI retrieval achieving a Recall@10 of up to 0.69 and a HIT@10 of 0.91. We also explored the performance of GUIClip for other GUI tasks including GUI classification and sketch-to-GUI retrieval with encouraging results.
Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human preferences. Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences, enabling more flexible and accurate language model alignment. In this paper, we propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game aimed at identifying the Nash equilibrium policy. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium. Additionally, we propose a new SPPO objective which is both strongly motivated by theory and is simple and effective in practice. In our experiments, using only 60k prompts (without responses) from the UltraFeedback dataset and without any prompt augmentation, by leveraging a pre-trained preference model PairRM with only 0.4B parameters, SPPO can obtain a model from fine-tuning Mistral-7B-Instruct-v0.2 that achieves the state-of-the-art length-controlled win-rate of 28.53% against GPT-4-Turbo on AlpacaEval 2.0. It also outperforms the (iterative) DPO and IPO on MT-Bench, Arena-Hard, and the Open LLM Leaderboard. Starting from a stronger base model Llama-3-8B-Instruct, we are able to achieve a length-controlled win rate of 38.77%. Notably, the strong performance of SPPO is achieved without additional external supervision (e.g., responses, preferences, etc.) from GPT-4 or other stronger language models. Codes are available at https://github.com/uclaml/SPPO.
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We explore the efficacy of popular model editing techniques - ROME, MEMIT, and EMMET, which are designed for precise layer interventions. We identify the most effective layers for targeted edits through an evaluation that encompasses up to 4096 edits across three distinct strategies: sequential editing, batch editing, and a hybrid approach we call as sequential-batch editing. Our findings indicate that increasing edit batch-sizes may degrade model performance more significantly than using smaller edit batches sequentially for equal number of edits. With this, we argue that sequential model editing is an important component for scaling model editing methods and future research should focus on methods that combine both batched and sequential editing. This observation suggests a potential limitation in current model editing methods which push towards bigger edit batch sizes, and we hope it paves way for future investigations into optimizing batch sizes and model editing performance.
Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation. Although quantized weights offer storage efficiency and allow for faster inference, existing works have indicated that quantization might compromise performance and exacerbate biases in LLMs. This study investigates the confidence and calibration of quantized models, considering factors such as language model type and scale as contributors to quantization loss. Firstly, we reveal that quantization with GPTQ to 4-bit results in a decrease in confidence regarding true labels, with varying impacts observed among different language models. Secondly, we observe fluctuations in the impact on confidence across different scales. Finally, we propose an explanation for quantization loss based on confidence levels, indicating that quantization disproportionately affects samples where the full model exhibited low confidence levels in the first place.
Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential for causal reasoning. In this work, we introduce Causal evaluation of Language Models (CaLM), which, to the best of our knowledge, is the first comprehensive benchmark for evaluating the causal reasoning capabilities of language models. First, we propose the CaLM framework, which establishes a foundational taxonomy consisting of four modules: causal target (i.e., what to evaluate), adaptation (i.e., how to obtain the results), metric (i.e., how to measure the results), and error (i.e., how to analyze the bad results). This taxonomy defines a broad evaluation design space while systematically selecting criteria and priorities. Second, we compose the CaLM dataset, comprising 126,334 data samples, to provide curated sets of causal targets, adaptations, metrics, and errors, offering extensive coverage for diverse research pursuits. Third, we conduct an extensive evaluation of 28 leading language models on a core set of 92 causal targets, 9 adaptations, 7 metrics, and 12 error types. Fourth, we perform detailed analyses of the evaluation results across various dimensions (e.g., adaptation, scale). Fifth, we present 50 high-level empirical findings across 9 dimensions (e.g., model), providing valuable guidance for future language model development. Finally, we develop a multifaceted platform, including a website, leaderboards, datasets, and toolkits, to support scalable and adaptable assessments. We envision CaLM as an ever-evolving benchmark for the community, systematically updated with new causal targets, adaptations, models, metrics, and error types to reflect ongoing research advancements. Project website is at https://opencausalab.github.io/CaLM.
Large language model alignment is widely used and studied to avoid LLM producing unhelpful and harmful responses. However, the lengthy training process and predefined preference bias hinder adaptation to online diverse human preferences. To this end, this paper proposes an alignment framework, called Reinforcement Learning with Human Behavior (RLHB), to align LLMs by directly leveraging real online human behaviors. By taking the generative adversarial framework, the generator is trained to respond following expected human behavior; while the discriminator tries to verify whether the triplets of query, response, and human behavior come from real online environments. Behavior modeling in natural-language form and the multi-model joint training mechanism enable an active and sustainable online alignment. Experimental results confirm the effectiveness of our proposed methods by both human and automatic evaluations.
This paper introduces CookingSense, a descriptive collection of knowledge assertions in the culinary domain extracted from various sources, including web data, scientific papers, and recipes, from which knowledge covering a broad range of aspects is acquired. CookingSense is constructed through a series of dictionary-based filtering and language model-based semantic filtering techniques, which results in a rich knowledgebase of multidisciplinary food-related assertions. Additionally, we present FoodBench, a novel benchmark to evaluate culinary decision support systems. From evaluations with FoodBench, we empirically prove that CookingSense improves the performance of retrieval augmented language models. We also validate the quality and variety of assertions in CookingSense through qualitative analysis.
Recent advancements in language models have demonstrated remarkable improvements in various natural language processing (NLP) tasks such as web navigation. Supervised learning (SL) approaches have achieved impressive performance while utilizing significantly less training data compared to previous methods. However, these SL-based models fall short when compared to reinforcement learning (RL) approaches, which have shown superior results. In this paper, we propose a novel approach that combines SL and RL techniques over the MiniWoB benchmark to leverage the strengths of both methods. We also address a critical limitation in previous models' understanding of HTML content, revealing a tendency to memorize target elements rather than comprehend the underlying structure. To rectify this, we propose methods to enhance true understanding and present a new baseline of results. Our experiments demonstrate that our approach outperforms previous SL methods on certain tasks using less data and narrows the performance gap with RL models, achieving 43.58\% average accuracy in SL and 36.69\% when combined with a multimodal RL approach. This study sets a new direction for future web navigation and offers insights into the limitations and potential of language modeling for computer tasks.
Compared to standard language model (LM) pretraining (i.e., from scratch), Knowledge Distillation (KD) entails an additional forward pass through a teacher model that is typically substantially larger than the target student model. As such, KD in LM pretraining materially slows down throughput of pretraining instances vis-a-vis pretraining from scratch. Scaling laws of LM pretraining suggest that smaller models can close the gap to larger counterparts if trained on more data (i.e., processing more tokens)-and under a fixed computation budget, smaller models are able be process more data than larger models. We thus hypothesize that KD might, in fact, be suboptimal to pretraining from scratch for obtaining smaller LMs, when appropriately accounting for the compute budget. To test this, we compare pretraining from scratch against several KD strategies for masked language modeling (MLM) in a fair experimental setup, with respect to amount of computation as well as pretraining data. Downstream results on GLUE, however, do not confirm our hypothesis: while pretraining from scratch performs comparably to ordinary KD under a fixed computation budget, more sophisticated KD strategies, namely TinyBERT (Jiao et al., 2020) and MiniLM (Wang et al., 2023), outperform it by a notable margin. We further find that KD yields larger gains over pretraining from scratch when the data must be repeated under the fixed computation budget.
The growth of social networks makes toxic content spread rapidly. Hate speech detection is a task to help decrease the number of harmful comments. With the diversity in the hate speech created by users, it is necessary to interpret the hate speech besides detecting it. Hence, we propose a methodology to construct a system for targeted hate speech detection from online streaming texts from social media. We first introduce the ViTHSD - a targeted hate speech detection dataset for Vietnamese Social Media Texts. The dataset contains 10K comments, each comment is labeled to specific targets with three levels: clean, offensive, and hate. There are 5 targets in the dataset, and each target is labeled with the corresponding level manually by humans with strict annotation guidelines. The inter-annotator agreement obtained from the dataset is 0.45 by Cohen's Kappa index, which is indicated as a moderate level. Then, we construct a baseline for this task by combining the Bi-GRU-LSTM-CNN with the pre-trained language model to leverage the power of text representation of BERTology. Finally, we suggest a methodology to integrate the baseline model for targeted hate speech detection into the online streaming system for practical application in preventing hateful and offensive content on social media.
While language models (LMs) offer significant capability in zero-shot reasoning tasks across a wide range of domains, they do not perform satisfactorily in problems which requires multi-step reasoning. Previous approaches to mitigate this involves breaking a larger, multi-step task into sub-tasks and asking the language model to generate proposals ("thoughts") for each sub-task and using exhaustive planning approaches such as DFS to compose a solution. In this work, we leverage this idea to introduce two new contributions: first, we formalize a planning-based approach to perform multi-step problem solving with LMs via Partially Observable Markov Decision Processes (POMDPs), with the LM's own reflections about the value of a state used as a search heuristic; second, leveraging the online POMDP solver POMCP, we demonstrate a superior success rate of 89.4% on the Game of 24 task as compared to existing approaches while also offering better anytime performance characteristics than fixed tree-search which is used previously. Taken together, these contributions allow modern LMs to decompose and solve larger-scale reasoning tasks more effectively.
Chain-of-Thought (CoT) reasoning often fails to faithfully reflect a language model's underlying decision process. We address this by making CoT text causally essential in a "Markovian" language model, factoring next-token prediction through an intermediate CoT and training it to predict future tokens independently of the original prompt. We formalize this via an "informativeness" objective that quantifies how much a trained CoT improves next-token predictions over a baseline. Using policy gradient, we show that Llama 3.1 8B achieves a 33.2% absolute accuracy improvement on GSM8K. Perturbation tests confirm stronger reliance on the CoT, while cross-model transfers indicate these reasoning traces generalize across interpreters. Our approach enhances both accuracy and interpretability, potentially extending CoT reasoning to arbitrarily long contexts and diverse tasks.