Language models, such as GPT-3.5 and ChatGPT, demonstrate remarkable abilities to follow diverse human instructions and perform a wide range of tasks. However, when probing language models using a range of basic table-understanding tasks, we observe that today's language models are still sub-optimal in many table-related tasks, likely because they are pre-trained predominantly on \emph{one-dimensional} natural-language texts, whereas relational tables are \emph{two-dimensional} objects. In this work, we propose a new "\emph{table-tuning}" paradigm, where we continue to train/fine-tune language models like GPT-3.5 and ChatGPT, using diverse table-tasks synthesized from real tables as training data, with the goal of enhancing language models' ability to understand tables and perform table tasks. We show that our resulting Table-GPT models demonstrate (1) better \emph{table-understanding} capabilities, by consistently outperforming the vanilla GPT-3.5 and ChatGPT, on a wide-range of table tasks, including holdout unseen tasks, and (2) strong \emph{generalizability}, in its ability to respond to diverse human instructions to perform new table-tasks, in a manner similar to GPT-3.5 and ChatGPT.

Legal Judgment Prediction (LJP) has become an increasingly crucial task in Legal AI, i.e., predicting the judgment of the case in terms of case fact description. Precedents are the previous legal cases with similar facts, which are the basis for the judgment of the subsequent case in national legal systems. Thus, it is worthwhile to explore the utilization of precedents in the LJP. Recent advances in deep learning have enabled a variety of techniques to be used to solve the LJP task. These can be broken down into two categories: large language models (LLMs) and domain-specific models. LLMs are capable of interpreting and generating complex natural language, while domain models are efficient in learning task-specific information. In this paper, we propose the precedent-enhanced LJP framework (PLJP), a system that leverages the strength of both LLM and domain models in the context of precedents. Specifically, the domain models are designed to provide candidate labels and find the proper precedents efficiently, and the large models will make the final prediction with an in-context precedents comprehension. Experiments on the real-world dataset demonstrate the effectiveness of our PLJP. Moreover, our work shows a promising direction for LLM and domain-model collaboration that can be generalized to other vertical domains.

Large Language Models (LLMs), like ChatGPT, are fundamentally tools trained on vast data, reflecting diverse societal impressions. This paper aims to investigate LLMs' self-perceived bias concerning indigeneity when simulating scenarios of indigenous people performing various roles. Through generating and analyzing multiple scenarios, this work offers a unique perspective on how technology perceives and potentially amplifies societal biases related to indigeneity in social computing. The findings offer insights into the broader implications of indigeneity in critical computing.

In today's digital era, the rapid spread of misinformation poses threats to public well-being and societal trust. As online misinformation proliferates, manual verification by fact checkers becomes increasingly challenging. We introduce FACT-GPT (Fact-checking Augmentation with Claim matching Task-oriented Generative Pre-trained Transformer), a framework designed to automate the claim matching phase of fact-checking using Large Language Models (LLMs). This framework identifies new social media content that either supports or contradicts claims previously debunked by fact-checkers. Our approach employs GPT-4 to generate a labeled dataset consisting of simulated social media posts. This data set serves as a training ground for fine-tuning more specialized LLMs. We evaluated FACT-GPT on an extensive dataset of social media content related to public health. The results indicate that our fine-tuned LLMs rival the performance of larger pre-trained LLMs in claim matching tasks, aligning closely with human annotations. This study achieves three key milestones: it provides an automated framework for enhanced fact-checking; demonstrates the potential of LLMs to complement human expertise; offers public resources, including datasets and models, to further research and applications in the fact-checking domain.

Large language models (LLMs) have gained enormous attention from both academia and industry, due to their exceptional ability in language generation and extremely powerful generalization. However, current LLMs still output unreliable content in practical reasoning tasks due to their inherent issues (e.g., hallucination). To better disentangle this problem, in this paper, we conduct an in-depth investigation to systematically explore the capability of LLMs in logical reasoning. More in detail, we first investigate the deficiency of LLMs in logical reasoning on different tasks, including event relation extraction and deductive reasoning. Our study demonstrates that LLMs are not good reasoners in solving tasks with rigorous reasoning and will produce counterfactual answers, which require us to iteratively refine. Therefore, we comprehensively explore different strategies to endow LLMs with logical reasoning ability, and thus enable them to generate more logically consistent answers across different scenarios. Based on our approach, we also contribute a synthesized dataset (LLM-LR) involving multi-hop reasoning for evaluation and pre-training. Extensive quantitative and qualitative analyses on different tasks also validate the effectiveness and necessity of teaching LLMs with logic and provide insights for solving practical tasks with LLMs in future work.

When applied to question answering and other text generation tasks, language models (LMs) may be queried generatively (by sampling answers from their output distribution) or discriminatively (by using them to score or rank a set of candidate outputs). These procedures sometimes yield very different predictions. How do we reconcile mutually incompatible scoring procedures to obtain coherent LM predictions? We introduce a new, a training-free, game-theoretic procedure for language model decoding. Our approach casts language model decoding as a regularized imperfect-information sequential signaling game - which we term the CONSENSUS GAME - in which a GENERATOR seeks to communicate an abstract correctness parameter using natural language sentences to a DISCRIMINATOR. We develop computational procedures for finding approximate equilibria of this game, resulting in a decoding algorithm we call EQUILIBRIUM-RANKING. Applied to a large number of tasks (including reading comprehension, commonsense reasoning, mathematical problem-solving, and dialog), EQUILIBRIUM-RANKING consistently, and sometimes substantially, improves performance over existing LM decoding procedures - on multiple benchmarks, we observe that applying EQUILIBRIUM-RANKING to LLaMA-7B outperforms the much larger LLaMA-65B and PaLM-540B models. These results highlight the promise of game-theoretic tools for addressing fundamental challenges of truthfulness and consistency in LMs.

Recently, large language models (LLMs), including notable models such as GPT-4 and burgeoning community models, have showcased significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a meticulously assembled General Logical Reasoning Evaluation benchmark comprised of 12 datasets that span three different types of tasks. Our experimental results show that compared to the performance of human and supervised fine-tuning, the logical reasoning capabilities of open LLM models necessitate additional improvement; ChatGPT and GPT-4 show a strong capability of logical reasoning, with GPT-4 surpassing ChatGPT by a large margin. We propose a self-consistency probing method to enhance the accuracy of ChatGPT and a fine-tuned method to boost the performance of an open LLM. We release the datasets and evaluation programs to facilitate future research.

Integrating large language models (LLMs) into healthcare presents potential but faces challenges. Directly pre-training LLMs for domains like medicine is resource-heavy and sometimes unfeasible. Sole reliance on Supervised Fine-tuning (SFT) can result in overconfident predictions and may not tap into domain specific insights. Addressing these challenges, we present a multi-stage training method combining Domain-specific Continued Pre-training (DCPT), SFT, and Direct Preference Optimization (DPO). A notable contribution of our study is the introduction of a 3Gb Chinese Medicine (ChiMed) dataset, encompassing medical question answering, plain texts, knowledge graphs, and dialogues, segmented into three training stages. The medical LLM trained with our pipeline, Qilin-Med, exhibits significant performance boosts. In the CPT and SFT phases, it achieves 38.4% and 40.0% accuracy on the CMExam, surpassing Baichuan-7B's 33.5%. In the DPO phase, on the Huatuo-26M test set, it scores 16.66 in BLEU-1 and 27.44 in ROUGE1, outperforming the SFT's 12.69 and 24.21. This highlights the strength of our training approach in refining LLMs for medical applications.

In the rapid development of artificial intelligence, solving complex AI tasks is a crucial technology in intelligent mobile networks. Despite the good performance of specialized AI models in intelligent mobile networks, they are unable to handle complicated AI tasks. To address this challenge, we propose Systematic Artificial Intelligence (SAI), which is a framework designed to solve AI tasks by leveraging Large Language Models (LLMs) and JSON-format intent-based input to connect self-designed model library and database. Specifically, we first design a multi-input component, which simultaneously integrates Large Language Models (LLMs) and JSON-format intent-based inputs to fulfill the diverse intent requirements of different users. In addition, we introduce a model library module based on model cards which employ model cards to pairwise match between different modules for model composition. Model cards contain the corresponding model's name and the required performance metrics. Then when receiving user network requirements, we execute each subtask for multiple selected model combinations and provide output based on the execution results and LLM feedback. By leveraging the language capabilities of LLMs and the abundant AI models in the model library, SAI can complete numerous complex AI tasks in the communication network, achieving impressive results in network optimization, resource allocation, and other challenging tasks.

Large Language Models (LLMs) have demonstrated remarkable human-level natural language generation capabilities. However, their potential to generate misinformation, often called the hallucination problem, poses a significant risk to their deployment. A common approach to address this issue is to retrieve relevant knowledge and fine-tune the LLM with the knowledge in its input. Unfortunately, this method incurs high training costs and may cause catastrophic forgetting for multi-tasking models. To overcome these limitations, we propose a knowledge-constrained decoding method called KCTS (Knowledge-Constrained Tree Search), which guides a frozen LM to generate text aligned with the reference knowledge at each decoding step using a knowledge classifier score and MCTS (Monte-Carlo Tree Search). To adapt the sequence-level knowledge classifier to token-level guidance, we also propose a novel token-level hallucination detection method called RIPA (Reward Inflection Point Approximation). Our empirical results on knowledge-grounded dialogue and abstractive summarization demonstrate the strength of KCTS as a plug-and-play, model-agnostic decoding method that can effectively reduce hallucinations in natural language generation.