The task of empowering large language models (LLMs) to accurately express their confidence, referred to as confidence elicitation, is essential in ensuring reliable and trustworthy decision-making processes. Previous methods, which primarily rely on model logits, have become less suitable for LLMs and even infeasible with the rise of closed-source LLMs (e.g., commercialized LLM APIs). This leads to a growing need to explore the untapped area of \emph{non-logit-based} approaches to estimate the uncertainty of LLMs. Hence, in this study, we investigate approaches for confidence elicitation that do not require model fine-tuning or access to proprietary information. We introduce three categories of methods: verbalize-based, consistency-based, and their hybrid methods for benchmarking, and evaluate their performance across five types of datasets and four widely-used LLMs. Our analysis of these methods uncovers several key insights: 1) LLMs often exhibit a high degree of overconfidence when verbalizing their confidence; 2) Prompting strategies such as CoT, Top-K and Multi-step confidences improve calibration of verbalized confidence; 3) Consistency-based methods outperform the verbalized confidences in most cases, with particularly notable improvements on the arithmetic reasoning task; 4) Hybrid methods consistently deliver the best performance over their baselines, thereby emerging as a promising state-of-the-art approach; 5) Despite these advancements, all investigated methods continue to struggle with challenging tasks, such as those requiring professional knowledge, leaving significant scope for improvement of confidence elicitation.

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human judgments, but recent research indicates that the lower-quality classical metrics remain dominant, one of the potential reasons being that their decision processes are more transparent. To foster more widespread acceptance of novel high-quality metrics, explainability thus becomes crucial. In this concept paper, we identify key properties as well as key goals of explainable machine translation metrics and provide a comprehensive synthesis of recent techniques, relating them to our established goals and properties. In this context, we also discuss the latest state-of-the-art approaches to explainable metrics based on generative models such as ChatGPT and GPT4. Finally, we contribute a vision of next-generation approaches, including natural language explanations. We hope that our work can help catalyze and guide future research on explainable evaluation metrics and, mediately, also contribute to better and more transparent machine translation systems.

As generative language models are deployed in ever-wider contexts, concerns about their political values have come to the forefront with critique from all parts of the political spectrum that the models are biased and lack neutrality. However, the question of what neutrality is and whether it is desirable remains underexplored. In this paper, I examine neutrality through an audit of Delphi [arXiv:2110.07574], a large language model designed for crowdsourced ethics. I analyse how Delphi responds to politically controversial questions compared to different US political subgroups. I find that Delphi is poorly calibrated with respect to confidence and exhibits a significant political skew. Based on these results, I examine the question of neutrality from a data-feminist lens, in terms of how notions of neutrality shift power and further marginalise unheard voices. These findings can hopefully contribute to a more reflexive debate about the normative questions of alignment and what role we want generative models to play in society.

We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Structured knowledge bases (KBs) are the backbone of many know\-ledge-intensive applications, and their automated construction has received considerable attention. In particular, open information extraction (OpenIE) is often used to induce structure from a text. However, although it allows high recall, the extracted knowledge tends to inherit noise from the sources and the OpenIE algorithm. Besides, OpenIE tuples contain an open-ended, non-canonicalized set of relations, making the extracted knowledge's downstream exploitation harder. In this paper, we study the problem of mapping an open KB into the fixed schema of an existing KB, specifically for the case of commonsense knowledge. We propose approaching the problem by generative translation, i.e., by training a language model to generate fixed-schema assertions from open ones. Experiments show that this approach occupies a sweet spot between traditional manual, rule-based, or classification-based canonicalization and purely generative KB construction like COMET. Moreover, it produces higher mapping accuracy than the former while avoiding the association-based noise of the latter.

Tactile sensing plays an irreplaceable role in robotic material recognition. It enables robots to distinguish material properties such as their local geometry and textures, especially for materials like textiles. However, most tactile recognition methods can only classify known materials that have been touched and trained with tactile data, yet cannot classify unknown materials that are not trained with tactile data. To solve this problem, we propose a tactile zero-shot learning framework to recognise unknown materials when they are touched for the first time without requiring training tactile samples. The visual modality, providing tactile cues from sight, and semantic attributes, giving high-level characteristics, are combined together to bridge the gap between touched classes and untouched classes. A generative model is learnt to synthesise tactile features according to corresponding visual images and semantic embeddings, and then a classifier can be trained using the synthesised tactile features of untouched materials for zero-shot recognition. Extensive experiments demonstrate that our proposed multimodal generative model can achieve a high recognition accuracy of 83.06% in classifying materials that were not touched before. The robotic experiment demo and the dataset are available at https://sites.google.com/view/multimodalzsl.

Interpreting the meaning of legal open-textured terms is a key task of legal professionals. An important source for this interpretation is how the term was applied in previous court cases. In this paper, we evaluate the performance of GPT-4 in generating factually accurate, clear and relevant explanations of terms in legislation. We compare the performance of a baseline setup, where GPT-4 is directly asked to explain a legal term, to an augmented approach, where a legal information retrieval module is used to provide relevant context to the model, in the form of sentences from case law. We found that the direct application of GPT-4 yields explanations that appear to be of very high quality on their surface. However, detailed analysis uncovered limitations in terms of the factual accuracy of the explanations. Further, we found that the augmentation leads to improved quality, and appears to eliminate the issue of hallucination, where models invent incorrect statements. These findings open the door to the building of systems that can autonomously retrieve relevant sentences from case law and condense them into a useful explanation for legal scholars, educators or practicing lawyers alike.

We present SweCTRL-Mini, a large Swedish language model that can be used for inference and fine-tuning on a single consumer-grade GPU. The model is based on the CTRL architecture by Keskar, McCann, Varshney, Xiong, and Socher (2019), which means that users of the SweCTRL-Mini model can control the genre of the generated text by inserting special tokens in the generation prompts. SweCTRL-Mini is trained on a subset of the Swedish part of the mC4 corpus and a set of Swedish novels. In this article, we provide (1) a detailed account of the utilized training data and text pre-processing steps, to the extent that it is possible to check whether a specific phrase/source was a part of the training data, and (2) an evaluation of the model on both discriminative tasks, using automatic evaluation methods, and generative tasks, using human referees. We also compare the generative capabilities of the model with those of GPT-3. SweCTRL-Mini is fully open and available for download.

Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate human-led prompting followed, with some progress achieved. In particular, subsequent work demonstrates automation can outperform fine-tuning in certain K-shot learning scenarios. In this paper, we revisit techniques for automated prompting on six different downstream tasks and a larger range of K-shot learning settings. We find that automated prompting does not consistently outperform simple manual prompts. Our work suggests that, in addition to fine-tuning, manual prompts should be used as a baseline in this line of research.

While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus (ARC), a visual intelligence benchmark introduced by Fran\c{c}ois Chollet, aims to assess how close AI systems are to human-like cognitive abilities. Most current approaches rely on carefully handcrafted domain-specific program searches to brute-force solutions for the tasks present in ARC. In this work, we propose a general learning-based framework for solving ARC. It is centered on transforming tasks from the vision to the language domain. This composition of language and vision allows for pre-trained models to be leveraged at each stage, enabling a shift from handcrafted priors towards the learned priors of the models. While not yet beating state-of-the-art models on ARC, we demonstrate the potential of our approach, for instance, by solving some ARC tasks that have not been solved previously.