Aspect sentiment quad prediction (ASQP) is a critical subtask of aspect-level sentiment analysis. Current ASQP datasets are characterized by their small size and low quadruple density, which hinders technical development. To expand capacity, we construct two large Chinese ASQP datasets crawled from multiple online platforms. The datasets hold several significant characteristics: larger size (each with 10,000+ samples) and rich aspect categories, more words per sentence, and higher density than existing ASQP datasets. Moreover, we are the first to evaluate the performance of Generative Pre-trained Transformer (GPT) series models on ASQP and exhibit potential issues. The experiments with state-of-the-art ASQP baselines underscore the need to explore additional techniques to address ASQP, as well as the importance of further investigation into methods to improve the performance of GPTs.

We show how to "compile" human-readable programs into standard decoder-only transformer models. Our compiler, Tracr, generates models with known structure. This structure can be used to design experiments. For example, we use it to study "superposition" in transformers that execute multi-step algorithms. Additionally, the known structure of Tracr-compiled models can serve as ground-truth for evaluating interpretability methods. Commonly, because the "programs" learned by transformers are unknown it is unclear whether an interpretation succeeded. We demonstrate our approach by implementing and examining programs including computing token frequencies, sorting, and parenthesis checking. We provide an open-source implementation of Tracr at https://github.com/google-deepmind/tracr.

A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round under the framework of in-context learning. This framework suffers the key disadvantage that the single-turn output generated by a single LLM might not deliver the perfect decision, just as humans sometimes need multiple attempts to get things right. This is especially true for the task of sentiment analysis where deep reasoning is required to address the complex linguistic phenomenon (e.g., clause composition, irony, etc) in the input. To address this issue, this paper introduces a multi-LLM negotiation framework for sentiment analysis. The framework consists of a reasoning-infused generator to provide decision along with rationale, a explanation-deriving discriminator to evaluate the credibility of the generator. The generator and the discriminator iterate until a consensus is reached. The proposed framework naturally addressed the aforementioned challenge, as we are able to take the complementary abilities of two LLMs, have them use rationale to persuade each other for correction. Experiments on a wide range of sentiment analysis benchmarks (SST-2, Movie Review, Twitter, yelp, amazon, IMDB) demonstrate the effectiveness of proposed approach: it consistently yields better performances than the ICL baseline across all benchmarks, and even superior performances to supervised baselines on the Twitter and movie review datasets.

Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue models fail to accurately express the external knowledge they rely upon. Inspired by previous work which identified that feed-forward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability {of FFNs} by knowledge enhancement and alignment respectively. We first propose \textsc{K-Dial}, which {explicitly} introduces {extended FFNs in Transformers to enhance factual knowledge expressions} given the specific patterns of knowledge-grounded dialogue inputs. Additionally, we apply the reinforcement learning for factual consistency (RLFC) method to implicitly adjust FFNs' expressions in responses by aligning with gold knowledge for the factual consistency preference. To comprehensively assess the factual consistency and dialogue quality of responses, we employ extensive automatic measures and human evaluations including sophisticated fine-grained NLI-based metrics. Experimental results on WoW and CMU\_DoG datasets demonstrate that our methods efficiently enhance the ability of the FFN module to convey factual knowledge, validating the efficacy of improving factual consistency for knowledge-grounded dialogue systems.

Knowledge graphs are often used to represent structured information in a flexible and efficient manner, but their use in situated dialogue remains under-explored. This paper presents a novel conversational model for human--robot interaction that rests upon a graph-based representation of the dialogue state. The knowledge graph representing the dialogue state is continuously updated with new observations from the robot sensors, including linguistic, situated and multimodal inputs, and is further enriched by other modules, in particular for spatial understanding. The neural conversational model employed to respond to user utterances relies on a simple but effective graph-to-text mechanism that traverses the dialogue state graph and converts the traversals into a natural language form. This conversion of the state graph into text is performed using a set of parameterized functions, and the values for those parameters are optimized based on a small set of Wizard-of-Oz interactions. After this conversion, the text representation of the dialogue state graph is included as part of the prompt of a large language model used to decode the agent response. The proposed approach is empirically evaluated through a user study with a humanoid robot that acts as conversation partner to evaluate the impact of the graph-to-text mechanism on the response generation. After moving a robot along a tour of an indoor environment, participants interacted with the robot using spoken dialogue and evaluated how well the robot was able to answer questions about what the robot observed during the tour. User scores show a statistically significant improvement in the perceived factuality of the robot responses when the graph-to-text approach is employed, compared to a baseline using inputs structured as semantic triples.

Moderating offensive, hateful, and toxic language has always been an important but challenging topic in the domain of safe use in NLP. The emerging large language models (LLMs), such as ChatGPT, can potentially further accentuate this threat. Previous works have discovered that ChatGPT can generate toxic responses using carefully crafted inputs. However, limited research has been done to systematically examine when ChatGPT generates toxic responses. In this paper, we comprehensively evaluate the toxicity in ChatGPT by utilizing instruction-tuning datasets that closely align with real-world scenarios. Our results show that ChatGPT's toxicity varies based on different properties and settings of the prompts, including tasks, domains, length, and languages. Notably, prompts in creative writing tasks can be 2x more likely than others to elicit toxic responses. Prompting in German and Portuguese can also double the response toxicity. Additionally, we discover that certain deliberately toxic prompts, designed in earlier studies, no longer yield harmful responses. We hope our discoveries can guide model developers to better regulate these AI systems and the users to avoid undesirable outputs.

Large language models (LLMs) excel in many tasks in NLP and beyond, but most open models have very limited coverage of smaller languages and LLM work tends to focus on languages where nearly unlimited data is available for pretraining. In this work, we study the challenges of creating LLMs for Finnish, a language spoken by less than 0.1% of the world population. We compile an extensive dataset of Finnish combining web crawls, news, social media and eBooks. We pursue two approaches to pretrain models: 1) we train seven monolingual models from scratch (186M to 13B parameters) dubbed FinGPT, 2) we continue the pretraining of the multilingual BLOOM model on a mix of its original training data and Finnish, resulting in a 176 billion parameter model we call BLUUMI. For model evaluation, we introduce FIN-bench, a version of BIG-bench with Finnish tasks. We also assess other model qualities such as toxicity and bias. Our models and tools are openly available at https://turkunlp.org/gpt3-finnish.

In this paper, we describe the capabilities and constraints of Large Language Models (LLMs) within disparate academic disciplines, aiming to delineate their strengths and limitations with precision. We examine how LLMs augment scientific inquiry, offering concrete examples such as accelerating literature review by summarizing vast numbers of publications, enhancing code development through automated syntax correction, and refining the scientific writing process. Simultaneously, we articulate the challenges LLMs face, including their reliance on extensive and sometimes biased datasets, and the potential ethical dilemmas stemming from their use. Our critical discussion extends to the varying impacts of LLMs across fields, from the natural sciences, where they help model complex biological sequences, to the social sciences, where they can parse large-scale qualitative data. We conclude by offering a nuanced perspective on how LLMs can be both a boon and a boundary to scientific progress.

The advent of large language models is reshaping computing education. Recent research has demonstrated that these models can produce better explanations than students, answer multiple-choice questions at or above the class average, and generate code that can pass automated tests in introductory courses. These capabilities have prompted instructors to rapidly adapt their courses and assessment methods to accommodate changes in learning objectives and the potential for academic integrity violations. While some scholars have advocated for the integration of visual problems as a safeguard against the capabilities of language models, new multimodal language models now have vision and language capabilities that may allow them to analyze and solve visual problems. In this paper, we evaluate the performance of two large multimodal models on visual assignments, with a specific focus on Parsons problems presented across diverse visual representations. Our results show that GPT-4V solved 96.7\% of these visual problems, struggling minimally with a single Parsons problem. Conversely, Bard performed poorly by only solving 69.2\% of problems, struggling with common issues like hallucinations and refusals. These findings suggest that merely transitioning to visual programming problems might not be a panacea to issues of academic integrity in the generative AI era.

Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations are relatively good, there remains a discernible gap comparing their performance with the few-shot setting. In this paper, we investigate the factors contributing to this gap and find that this gap can largely be closed (for about 70%) by matching the writing styles of the target corpus. Additionally, we explore potential approaches to enhance zero-shot baselines without the need for parallel demonstration examples, providing valuable insights into how these methods contribute to improving translation metrics.