In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM's performance exceeds humans and surpasses the performance of state-of-the-art methods fine-tuned on extensive datasets in debate evaluation. We additionally explore and analyze biases present in LLMs, including positional bias, lexical bias, order bias, which may affect their evaluative judgments. Our findings reveal a consistent bias in both GPT-3.5 and GPT-4 towards the second candidate response presented, attributed to prompt design. We also uncover lexical biases in both GPT-3.5 and GPT-4, especially when label sets carry connotations such as numerical or sequential, highlighting the critical need for careful label verbalizer selection in prompt design. Additionally, our analysis indicates a tendency of both models to favor the debate's concluding side as the winner, suggesting an end-of-discussion bias.

Recent advancements in Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in reproducibility. This paper conducts a critical evaluation of CoT prompting, extending beyond arithmetic to include complex logical and commonsense reasoning tasks, areas where standard CoT methods fall short. We propose the integration of human-like heuristics and shortcuts into language models (LMs) through "break the chain" strategies. These strategies disrupt traditional CoT processes using controlled variables to assess their efficacy. Additionally, we develop innovative zero-shot prompting strategies that encourage the use of shortcuts, enabling LMs to quickly exploit reasoning clues and bypass detailed procedural steps. Our comprehensive experiments across various LMs, both commercial and open-source, reveal that LMs maintain effective performance with "break the chain" strategies. We also introduce ShortcutQA, a dataset specifically designed to evaluate reasoning through shortcuts, compiled from competitive tests optimized for heuristic reasoning tasks such as forward/backward reasoning and simplification. Our analysis confirms that ShortcutQA not only poses a robust challenge to LMs but also serves as an essential benchmark for enhancing reasoning efficiency in AI.

This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM's reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract logic problem generalize to contextualized logic problems and vice versa? To investigate these questions, we focus on standard propositional logic, specifically propositional deductive and abductive logic reasoning. In particular, we construct instantiated datasets for deductive and abductive reasoning with 4 levels of difficulty, encompassing 12 distinct categories or domains based on the categorization of Wikipedia. Our experiments aim to provide insights into disentangling context in logical reasoning and the true reasoning capabilities of LLMs and their generalization potential. The code and dataset are available at: https://github.com/agiresearch/ContextHub.

For entity recognition - including classification Named Entity Recognition (NER) and Relation and linking - and relation classification problems, Extraction (RE) allow for the extraction and categorization recent ZSL methods (Aly et al., 2021; Ledell Wu, of structured data from unstructured 2020; Chen and Li, 2021) rely on textual descriptions text, which in turn enables not only more accurate of entities or relations. Descriptions provide entity recognition and relationship extraction, but the required information about the semantics of entities also getting data from several unstructured sources, (or relations), which help the models to identify helping to build knowledge graphs and the semantic entity mentions in texts without observing them web. However, these methods usually rely on during training. Works such as (Ledell Wu, 2020; labeled data (usually human-annotated data) for a De Cao et al., 2021) and (Aly et al., 2021) show good performance, usually requiring domain experts how effective it is to use textual descriptions to perform for data acquisition and labeling, which may entity recognition tasks in the zero-shot context.

Human-robot collaboration, in which the robot intelligently assists the human with the upcoming task, is an appealing objective. To achieve this goal, the agent needs to be equipped with a fundamental collaborative navigation ability, where the agent should reason human intention by observing human activities and then navigate to the human's intended destination in advance of the human. However, this vital ability has not been well studied in previous literature. To fill this gap, we propose a collaborative navigation (CoNav) benchmark. Our CoNav tackles the critical challenge of constructing a 3D navigation environment with realistic and diverse human activities. To achieve this, we design a novel LLM-based humanoid animation generation framework, which is conditioned on both text descriptions and environmental context. The generated humanoid trajectory obeys the environmental context and can be easily integrated into popular simulators. We empirically find that the existing navigation methods struggle in CoNav task since they neglect the perception of human intention. To solve this problem, we propose an intention-aware agent for reasoning both long-term and short-term human intention. The agent predicts navigation action based on the predicted intention and panoramic observation. The emergent agent behavior including observing humans, avoiding human collision, and navigation reveals the efficiency of the proposed datasets and agents.

The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events. We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, temporal sequencing, and future event forecasting. In the experiment, we leverage retrieval-augmented generation (RAG) method and LLMs with long context window to deal with lengthy news articles of TCE. Our findings indicate that models with suitable retrievers exhibit comparable performance with those utilizing long context window.

In the modern era, mobile phones have become ubiquitous, and Short Message Service (SMS) has grown to become a multi-million-dollar service due to the widespread adoption of mobile devices and the millions of people who use SMS daily. However, SMS spam has also become a pervasive problem that endangers users' privacy and security through phishing and fraud. Despite numerous spam filtering techniques, there is still a need for a more effective solution to address this problem [1]. This research addresses the pervasive issue of SMS spam, which poses threats to users' privacy and security. Despite existing spam filtering techniques, the high false-positive rate persists as a challenge. The study introduces a novel approach utilizing Natural Language Processing (NLP) and machine learning models, particularly BERT (Bidirectional Encoder Representations from Transformers), for SMS spam detection and classification. Data preprocessing techniques, such as stop word removal and tokenization, are applied, along with feature extraction using BERT. Machine learning models, including SVM, Logistic Regression, Naive Bayes, Gradient Boosting, and Random Forest, are integrated with BERT for differentiating spam from ham messages. Evaluation results revealed that the Na\"ive Bayes classifier + BERT model achieves the highest accuracy at 97.31% with the fastest execution time of 0.3 seconds on the test dataset. This approach demonstrates a notable enhancement in spam detection efficiency and a low false-positive rate. The developed model presents a valuable solution to combat SMS spam, ensuring faster and more accurate detection. This model not only safeguards users' privacy but also assists network providers in effectively identifying and blocking SMS spam messages.

The emergence of large language models (LLMs) has increasingly drawn attention to the use of LLMs for human-like planning. Existing work on LLM-based planning either focuses on leveraging the inherent language generation capabilities of LLMs to produce free-style plans, or employs reinforcement learning approaches to learn decision-making for a limited set of actions within restricted environments. However, both approaches exhibit significant discrepancies from the open and executable requirements in real-world planning. In this paper, we propose a new planning task--open grounded planning. The primary objective of open grounded planning is to ask the model to generate an executable plan based on a variable action set, thereby ensuring the executability of the produced plan. To this end, we establishes a benchmark for open grounded planning spanning a wide range of domains. Then we test current state-of-the-art LLMs along with five planning approaches, revealing that existing LLMs and methods still struggle to address the challenges posed by grounded planning in open domains. The outcomes of this paper define and establish a foundational dataset for open grounded planning, and shed light on the potential challenges and future directions of LLM-based planning.

Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with supervised methods, comprehensive efforts to assess SSL's impact on machine learning fairness (i.e., performing equally on different demographic breakdowns) are lacking. Hypothesizing that SSL models would learn more generic, hence less biased representations, this study explores the impact of pre-training and fine-tuning strategies on fairness. We introduce a fairness assessment framework for SSL, comprising five stages: defining dataset requirements, pre-training, fine-tuning with gradual unfreezing, assessing representation similarity conditioned on demographics, and establishing domain-specific evaluation processes. We evaluate our method's generalizability on three real-world human-centric datasets (i.e., MIMIC, MESA, and GLOBEM) by systematically comparing hundreds of SSL and fine-tuned models on various dimensions spanning from the intermediate representations to appropriate evaluation metrics. Our findings demonstrate that SSL can significantly improve model fairness, while maintaining performance on par with supervised methods-exhibiting up to a 30% increase in fairness with minimal loss in performance through self-supervision. We posit that such differences can be attributed to representation dissimilarities found between the best- and the worst-performing demographics across models-up to x13 greater for protected attributes with larger performance discrepancies between segments.

Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech, the facial and body movements of the speakers, as well as the texts and pictures in the slides and possibly even the papers. Although multiple academic video datasets have been constructed and released, few of them support both multimodal content recognition and understanding tasks, which is partially due to the lack of high-quality human annotations. In this paper, we propose a novel multimodal, multigenre, and multipurpose audio-visual academic lecture dataset (M$^3$AV), which has almost 367 hours of videos from five sources covering computer science, mathematics, and medical and biology topics. With high-quality human annotations of the slide text and spoken words, in particular high-valued name entities, the dataset can be used for multiple audio-visual recognition and understanding tasks. Evaluations performed on contextual speech recognition, speech synthesis, and slide and script generation tasks demonstrate that the diversity of M$^3$AV makes it a challenging dataset.