Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects by shifting the distribution of generated text towards a desired style, e.g., a set of topics. Subsequently, the resulting summaries may be tailored to user-defined requirements. This paper presents a new Transformer-based architecture capable of producing topic-focused summaries. The architecture modifies the cross-attention mechanism of the Transformer to bring topic-focus control to the generation process while not adding any further parameters to the model. We show that our model sets a new state of the art on the NEWTS dataset in terms of topic-focused abstractive summarization as well as a topic-prevalence score. Moreover, we show via extensive experiments that our proposed topical cross-attention mechanism can be plugged into various Transformer models, such as BART and T5, improving their performance on the CNN/Dailymail and XSum benchmark datasets for abstractive summarization. This is achieved via fine-tuning, without requiring training from scratch. Finally, we show through human evaluation that our model generates more faithful summaries outperforming the state-of-the-art Frost model.
Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations hurts downstream performance, outlier dimensions are detrimental to the representational quality of embeddings. In this study, we investigate how fine-tuning impacts outlier dimensions and show that 1) outlier dimensions that occur in pre-training persist in fine-tuned models and 2) a single outlier dimension can complete downstream tasks with a minimal error rate. Our results suggest that outlier dimensions can encode crucial task-specific knowledge and that the value of a representation in a single outlier dimension drives downstream model decisions.
Recent work in mechanistic interpretability has shown that behaviors in language models can be successfully reverse-engineered through circuit analysis. A common criticism, however, is that each circuit is task-specific, and thus such analysis cannot contribute to understanding the models at a higher level. In this work, we present evidence that insights (both low-level findings about specific heads and higher-level findings about general algorithms) can indeed generalize across tasks. Specifically, we study the circuit discovered in Wang et al. (2022) for the Indirect Object Identification (IOI) task and 1.) show that it reproduces on a larger GPT2 model, and 2.) that it is mostly reused to solve a seemingly different task: Colored Objects (Ippolito & Callison-Burch, 2023). We provide evidence that the process underlying both tasks is functionally very similar, and contains about a 78% overlap in in-circuit attention heads. We further present a proof-of-concept intervention experiment, in which we adjust four attention heads in middle layers in order to 'repair' the Colored Objects circuit and make it behave like the IOI circuit. In doing so, we boost accuracy from 49.6% to 93.7% on the Colored Objects task and explain most sources of error. The intervention affects downstream attention heads in specific ways predicted by their interactions in the IOI circuit, indicating that this subcircuit behavior is invariant to the different task inputs. Overall, our results provide evidence that it may yet be possible to explain large language models' behavior in terms of a relatively small number of interpretable task-general algorithmic building blocks and computational components.
Societal biases that are contained in retrieved documents have received increased interest. Such biases, which are often prevalent in the training data and learned by the model, can cause societal harms, by misrepresenting certain groups, and by enforcing stereotypes. Mitigating such biases demands algorithms that balance the trade-off between maximized utility for the user with fairness objectives, which incentivize unbiased rankings. Prior work on bias mitigation often assumes that ranking scores, which correspond to the utility that a document holds for a user, can be accurately determined. In reality, there is always a degree of uncertainty in the estimate of expected document utility. This uncertainty can be approximated by viewing ranking models through a Bayesian perspective, where the standard deterministic score becomes a distribution. In this work, we investigate whether uncertainty estimates can be used to decrease the amount of bias in the ranked results, while minimizing loss in measured utility. We introduce a simple method that uses the uncertainty of the ranking scores for an uncertainty-aware, post hoc approach to bias mitigation. We compare our proposed method with existing baselines for bias mitigation with respect to the utility-fairness trade-off, the controllability of methods, and computational costs. We show that an uncertainty-based approach can provide an intuitive and flexible trade-off that outperforms all baselines without additional training requirements, allowing for the post hoc use of this approach on top of arbitrary retrieval models.
Multimodal learning models have become increasingly important as they surpass single-modality approaches on diverse tasks ranging from question-answering to autonomous driving. Despite the importance of multimodal learning, existing efforts focus on NLP applications, where the number of modalities is typically less than four (audio, video, text, images). However, data inputs in other domains, such as the medical field, may include X-rays, PET scans, MRIs, genetic screening, clinical notes, and more, creating a need for both efficient and accurate information fusion. Many state-of-the-art models rely on pairwise cross-modal attention, which does not scale well for applications with more than three modalities. For $n$ modalities, computing attention will result in $n \choose 2$ operations, potentially requiring considerable amounts of computational resources. To address this, we propose a new domain-neutral attention mechanism, One-Versus-Others (OvO) attention, that scales linearly with the number of modalities and requires only $n$ attention operations, thus offering a significant reduction in computational complexity compared to existing cross-modal attention algorithms. Using three diverse real-world datasets as well as an additional simulation experiment, we show that our method improves performance compared to popular fusion techniques while decreasing computation costs.
Explainable Information Retrieval (XIR) is a growing research area focused on enhancing transparency and trustworthiness of the complex decision-making processes taking place in modern information retrieval systems. While there has been progress in developing XIR systems, empirical evaluation tools to assess the degree of explainability attained by such systems are lacking. To close this gap and gain insights into the true merit of XIR systems, we extend existing insights from a factor analysis of search explainability to introduce SSE (Search System Explainability), an evaluation metric for XIR search systems. Through a crowdsourced user study, we demonstrate SSE's ability to distinguish between explainable and non-explainable systems, showing that systems with higher scores indeed indicate greater interpretability. Additionally, we observe comparable perceived temporal demand and performance levels between non-native and native English speakers. We hope that aside from these concrete contributions to XIR, this line of work will serve as a blueprint for similar explainability evaluation efforts in other domains of machine learning and natural language processing.
Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that LLM representations are dominated by a few ``outlier dimensions'' with exceedingly high variance and magnitude. Several studies in Natural Language Processing (NLP) have sought to mitigate the impact of such outlier dimensions and force LLMs to be isotropic (i.e., have uniform variance across all dimensions in embedding space). Isotropy is thought to be a desirable property for LLMs that improves model performance and more closely aligns textual representations with human intuition. However, many of the claims regarding isotropy in NLP have been based on the average cosine similarity of embeddings, which has recently been shown to be a flawed measure of isotropy. In this paper, we propose I-STAR: IsoScore$^{\star}$-based STable Anisotropic Regularization, a novel regularization method that can be used to increase or decrease levels of isotropy in embedding space during training. I-STAR uses IsoScore$^{\star}$, the first accurate measure of isotropy that is both differentiable and stable on mini-batch computations. In contrast to several previous works, we find that \textit{decreasing} isotropy in contextualized embeddings improves performance on the majority of tasks and models considered in this paper.
A primary criticism towards language models (LMs) is their inscrutability. This paper presents evidence that, despite their size and complexity, LMs sometimes exploit a computational mechanism familiar from traditional word embeddings: the use of simple vector arithmetic in order to encode abstract relations (e.g., Poland:Warsaw::China:Beijing). We investigate a range of language model sizes (from 124M parameters to 176B parameters) in an in-context learning setting, and find that for a variety of tasks (involving capital cities, upper-casing, and past-tensing), a key part of the mechanism reduces to a simple linear update applied by the feedforward networks. We further show that this mechanism is specific to tasks that require retrieval from pretraining memory, rather than retrieval from local context. Our results contribute to a growing body of work on the mechanistic interpretability of LLMs, and offer reason to be optimistic that, despite the massive and non-linear nature of the models, the strategies they ultimately use to solve tasks can sometimes reduce to familiar and even intuitive algorithms.
Sparse annotation poses persistent challenges to training dense retrieval models, such as the problem of false negatives, i.e. unlabeled relevant documents that are spuriously used as negatives in contrastive learning, distorting the training signal. To alleviate this problem, we introduce evidence-based label smoothing, a computationally efficient method that prevents penalizing the model for assigning high relevance to false negatives. To compute the target relevance distribution over candidate documents within the ranking context of a given query, candidates most similar to the ground truth are assigned a non-zero relevance probability based on the degree of their similarity to the ground-truth document(s). As a relevance estimate we leverage an improved similarity metric based on reciprocal nearest neighbors, which can also be used independently to rerank candidates in post-processing. Through extensive experiments on two large-scale ad hoc text retrieval datasets we demonstrate that both methods can improve the ranking effectiveness of dense retrieval models.
Hospital discharge documentation is among the most essential, yet time-consuming documents written by medical practitioners. The objective of this study was to automatically generate hospital discharge summaries using neural network summarization models. We studied various data preparation and neural network training techniques that generate discharge summaries. Using nursing notes and discharge summaries from the MIMIC-III dataset, we studied the viability of the automatic generation of various sections of a discharge summary using four state-of-the-art neural network summarization models (BART, T5, Longformer and FLAN-T5). Our experiments indicated that training environments including nursing notes as the source, and discrete sections of the discharge summary as the target output (e.g. "History of Present Illness") improve language model efficiency and text quality. According to our findings, the fine-tuned BART model improved its ROUGE F1 score by 43.6% against its standard off-the-shelf version. We also found that fine-tuning the baseline BART model with other setups caused different degrees of improvement (up to 80% relative improvement). We also observed that a fine-tuned T5 generally achieves higher ROUGE F1 scores than other fine-tuned models and a fine-tuned FLAN-T5 achieves the highest ROUGE score overall, i.e., 45.6. For majority of the fine-tuned language models, summarizing discharge summary report sections separately outperformed the summarization the entire report quantitatively. On the other hand, fine-tuning language models that were previously instruction fine-tuned showed better performance in summarizing entire reports. This study concludes that a focused dataset designed for the automatic generation of discharge summaries by a language model can produce coherent Discharge Summary sections.