Exploring alternative ideas by rewriting text is integral to the writing process. State-of-the-art large language models (LLMs) can simplify writing variation generation. However, current interfaces pose challenges for simultaneous consideration of multiple variations: creating new versions without overwriting text can be difficult, and pasting them sequentially can clutter documents, increasing workload and disrupting writers' flow. To tackle this, we present ABScribe, an interface that supports rapid, yet visually structured, exploration of writing variations in human-AI co-writing tasks. With ABScribe, users can swiftly produce multiple variations using LLM prompts, which are auto-converted into reusable buttons. Variations are stored adjacently within text segments for rapid in-place comparisons using mouse-over interactions on a context toolbar. Our user study with 12 writers shows that ABScribe significantly reduces task workload (d = 1.20, p < 0.001), enhances user perceptions of the revision process (d = 2.41, p < 0.001) compared to a popular baseline workflow, and provides insights into how writers explore variations using LLMs.

Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal model for music understanding. We detail our process for dataset creation, which involves augmenting the annotations of diverse open-source music datasets and converting them to a unified instruction-tuning format. We propose a multimodal architecture for LLark, integrating a pretrained generative model for music with a pretrained language model. In evaluations on three types of tasks (music understanding, captioning, and reasoning), we show that our model matches or outperforms existing baselines in zero-shot generalization for music understanding, and that humans show a high degree of agreement with the model's responses in captioning and reasoning tasks. LLark is trained entirely from open-source music data and models, and we make our training code available along with the release of this paper. Additional results and audio examples are at https://bit.ly/llark, and our source code is available at https://github.com/spotify-research/llark .

Recent advances in text-to-speech have made it possible to generate natural-sounding audio from text. However, audiobook narrations involve dramatic vocalizations and intonations by the reader, with greater reliance on emotions, dialogues, and descriptions in the narrative. Using our dataset of 93 aligned book-audiobook pairs, we present improved models for prosody prediction properties (pitch, volume, and rate of speech) from narrative text using language modeling. Our predicted prosody attributes correlate much better with human audiobook readings than results from a state-of-the-art commercial TTS system: our predicted pitch shows a higher correlation with human reading for 22 out of the 24 books, while our predicted volume attribute proves more similar to human reading for 23 out of the 24 books. Finally, we present a human evaluation study to quantify the extent that people prefer prosody-enhanced audiobook readings over commercial text-to-speech systems.

Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called UNIQORN, builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. UNIQORN copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that UNIQORN significantly outperforms state-of-the-art methods for heterogeneous QA -- in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process.

We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard finetuning of LLaMA-2-7B using Alpaca achieves 29.79% on AlpacaEval, which rises to 64.69% using noisy embeddings. NEFTune also improves over strong baselines on modern instruction datasets. Models trained with Evol-Instruct see a 10% improvement, with ShareGPT an 8% improvement, and with OpenPlatypus an 8% improvement. Even powerful models further refined with RLHF such as LLaMA-2-Chat benefit from additional training with NEFTune. The ability of LLMs to follow detailed instructions is vital to their usefulness. Generative language models are typically trained on raw web data, and then subsequently fine-tuned on a comparatively small but carefully curated set of instruction data. Instruction fine-tuning is crucial to taming the power of LLMs, and the usefulness of a model is largely determined by our ability to get the most out of small instruction datasets. In this paper, we propose to add random noise to the embedding vectors of the training data during the forward pass of fine-tuning. We show that this simple trick can improve the outcome of instruction fine-tuning, often by a large margin, with no additional compute or data overhead. Noisy Embedding Instruction Fine Tuning (NEFTune), while simple, has a strong impact on downstream conversational quality. When a raw LLM like LLaMA-2-7B is finetuned with noisy embeddings, its performance on AlpacaEval improves from 29.8% to 64.7% (Figure 1) - an impressive boost of around 35 percentage points (Touvron et al., 2023b; Dubois et al., 2023). NEFTune leads to this surprising and large jump in performance on conversational tasks, maintaining performance on factual question answering baselines. This technique seems to be a free lunch for LLM fine-tuning. NEFTune leads to massive performance boosts across all of these datasets, showcasing the increased conversational quality of the generated answers. The earliest forms of instruction finetuning such as FLAN and T0 (Sanh et al., 2021; Wei et al., 2021) focused on cross-task generalization in language models. Encoder-decoder language models were finetuned on a broad range of NLP tasks (about 100) and then evaluated on a set of different tasks. This was later scaled up to include thousands of tasks, seeing further improvement over the original FLAN (Chung et al., 2022; Xu et al., 2022). Although these works showed that LLMs could be easily adapted to solve simple and classical NLP tasks, real-world scenarios require LLMs to provide free-form answers to open-ended queries. InstructGPT (Ouyang et al., 2022) was the first model to tackle open-ended queries with impressive performance. OpenAI further trained GPT-3 (Brown et al., 2020) using reinforcement learning from human feedback (RLHF) to align the model.

Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs. To this end, a fine-grained audio-visual joint representation (FAVOR) learning framework for multimodal LLMs is proposed in this paper, which extends a text-based LLM to simultaneously perceive speech and audio events in the audio input stream and images or videos in the visual input stream, at the frame level. To fuse the audio and visual feature streams into joint representations and to align the joint space with the LLM input embedding space, we propose a causal Q-Former structure with a causal attention module to enhance the capture of causal relations of the audio-visual frames across time. An audio-visual evaluation benchmark (AVEB) is also proposed which comprises six representative single-modal tasks with five cross-modal tasks reflecting audio-visual coreasoning abilities. While achieving competitive single-modal performance on audio, speech and image tasks in AVEB, FAVOR achieved over 20% accuracy improvements on the video question-answering task when fine-grained information or temporal causal reasoning is required. FAVOR, in addition, demonstrated remarkable video comprehension and reasoning abilities on tasks that are unprecedented by other multimodal LLMs. Text-based large language models (LLM) (Brown et al., 2020; Touvron et al., 2023; Chiang et al., 2023; Anil et al., 2023; Du et al., 2022) have demonstrated remarkable performance in various natural language processing tasks, especially achieving human-level capabilities in reasoning and comprehension (OpenAI, 2023). Meanwhile, instruction fine-tuning (Chung et al., 2022; Ouyang et al., 2022; Peng et al., 2023), where data is organised as pairs of user instruction (or prompt) and reference response, has emerged as a training paradigm that enables LLMs to perform various tasks by following open-ended natural language instructions from non-expert users. Recently, there has been a burgeoning research interest in equipping LLMs with visual and auditory perception abilities. These investigations often employ a trained modality alignment module that aligns the representation space of the input modality with the text one. Subsequently, work has started looking at incorporating multiple simultaneous input modalities (Su et al., 2023; Zhang et al., 2023b; Lyu et al., 2023; Zhao et al., 2023; Chen et al., 2023a). Despite the sequential nature of video and audio inputs, most aforementioned work treated video as a sampled subset of individual images and audio as a fixed-length spectrogram.

While large language models (LLMs) have shown impressive results for more objective tasks such as QA and retrieval, it remains nontrivial to evaluate their performance on open-ended text generation for reasons including (1) data contamination; (2) multi-dimensional evaluation criteria; and (3) subjectiveness stemming from reviewers' personal preferences. To address such issues, we propose to model personalization in an uncontaminated open-ended generation assessment. We create two new datasets Per-MPST and Per-DOC for personalized story evaluation, by re-purposing existing datasets with proper anonymization and new personalized labels. SE to infer reviewer preferences and provide a personalized evaluation. SE predicts either a detailed review or fine-grained comparison in several aspects (such as interestingness and surprise) for that reviewer on a new text input. SE outperforms GPT-4 by 15.8% on Kendall correlation of story ratings, and by 13.7% on pairwise preference prediction accuracy. Both datasets and code will be released. LLMs' abilities in open-ended text generation are still insufficiently Meanwhile, some recent metrics propose to directly use strong LLMs as evaluators (Fu et al., 2023; Liu et al., Besides, the contamination problem may affect the evaluation performance, similar to other tasks (Chang et al., 2023). Human evaluation is also widely used in open-ended text generation. However, it may be timeconsuming and expensive, especially for larger-scale evaluation. This personalization issue in text generation has recently attracted increasing attention (Flek, 2020; Dudy et al., 2021), but personalization in evaluation is still under-explored. In this paper, we explore personalized evaluation for long-form story generation, where the assessment is heavily influenced by reviewers' personal preferences. For example, Figure 1 illustrates two reviewers' opinions when comparing two plots derived from the same premise. Reviewer 1 prefers Plot A for its uplifting ending while Reviewer 2 favors Plot B because of the plot complexity and empathetic ending. To model such diverse preferences in story evaluation, the major difficulty lies in the following aspects: personalization story evaluation dataset modeling, i.e., uncontaminated story datasets with personal information, and reviewer preference modeling, i.e., effective methods to capture reviewer preferences and evaluate stories from a particular individual's perspective. Few story evaluation datasets have personal labels due to the difficulty of collecting personal information. Besides, most existing story datasets have been exposed to LLMs.

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is designed to be human readable, punctuation is added, numbers are presented in Arabic numeric form and abbreviations are included. Additionally, these models have a tendency to skip disfluencies and hesitations in the output. Though useful for readability, these attributes are not helpful for assessing the ability of a candidate and providing feedback. Here a precise transcription of what a candidate said is needed. In this paper, we give a detailed analysis of Whisper outputs and propose two solutions: fine-tuning and soft prompt tuning. Experiments are conducted on both public speech corpora and an English learner dataset. Results show that we can effectively alter the decoding behaviour of Whisper to generate the exact words spoken in the response.

Topological Data Analysis (TDA) has been successfully used for various tasks in signal/image processing, from visualization to supervised/unsupervised classification. Often, topological characteristics are obtained from persistent homology theory. The standard TDA pipeline starts from the raw signal data or a representation of it. Then, it consists in building a multiscale topological structure on the top of the data using a pre-specified filtration, and finally to compute the topological signature to be further exploited. The commonly used topological signature is a persistent diagram (or transformations of it). Current research discusses the consequences of the many ways to exploit topological signatures, much less often the choice of the filtration, but to the best of our knowledge, the choice of the representation of a signal has not been the subject of any study yet. This paper attempts to provide some answers on the latter problem. To this end, we collected real audio data and built a comparative study to assess the quality of the discriminant information of the topological signatures extracted from three different representation spaces. Each audio signal is represented as i) an embedding of observed data in a higher dimensional space using Taken's representation, ii) a spectrogram viewed as a surface in a 3D ambient space, iii) the set of spectrogram's zeroes. From vowel audio recordings, we use topological signature for three prediction problems: speaker gender, vowel type, and individual. We show that topologically-augmented random forest improves the Out-of-Bag Error (OOB) over solely based Mel-Frequency Cepstral Coefficients (MFCC) for the last two problems. Our results also suggest that the topological information extracted from different signal representations is complementary, and that spectrogram's zeros offers the best improvement for gender prediction.

A British computer scientist who earned the nickname "the Godfather of AI" warned that the dangers of artifical intelligence made famous in films like "The Terminator" could become more reality than fiction. "I think in five years' time, it may well be able to reason better than us," Geoffrey Hinton, a British computer scientist and cognitive psychologist, said during an interview with "60 Minutes," according to a report from Yahoo News. Hinton, who became well known for his work on the framework for AI, urged caution in the continued development of AI technology, questioning whether humans can fully understand the technology that is currently seeing rapid development. "I think we're moving into a period when for the first time ever, we have things more intelligent than us," Hinton said. Hinton argued that while humans develop the algorithm AI tools use to learn, they have little understanding of how that learning actually takes place.