Paul McNamee

James Mayfield, Eugene Yang, Dawn Lawrie et al. · allen-ai

Large Language Models (LLMs) have enabled new ways to satisfy information needs. Although great strides have been made in applying them to settings like document ranking and short-form text generation, they still struggle to compose complete, accurate, and verifiable long-form reports. Reports with these qualities are necessary to satisfy the complex, nuanced, or multi-faceted information needs of users. In this perspective paper, we draw together opinions from industry and academia, and from a variety of related research areas, to present our vision for automatic report generation, and -- critically -- a flexible framework by which such reports can be evaluated. In contrast with other summarization tasks, automatic report generation starts with a detailed description of an information need, stating the necessary background, requirements, and scope of the report. Further, the generated reports should be complete, accurate, and verifiable. These qualities, which are desirable -- if not required -- in many analytic report-writing settings, require rethinking how to build and evaluate systems that exhibit these qualities. To foster new efforts in building these systems, we present an evaluation framework that draws on ideas found in various evaluations. To test completeness and accuracy, the framework uses nuggets of information, expressed as questions and answers, that need to be part of any high-quality generated report. Additionally, evaluation of citations that map claims made in the report to their source documents ensures verifiability.

Dayeon Ki, Marine Carpuat, Paul McNamee et al.

Multilingual Retrieval-Augmented Generation (mRAG) systems enable language models to answer knowledge-intensive queries with citation-supported responses across languages. While such systems have been proposed, an open questions is whether the mixture of different document languages impacts generation and citation in unintended ways. To investigate, we introduce a controlled methodology using model internals to measure language preference while holding other factors such as document relevance constant. Across eight languages and six open-weight models, we find that models preferentially cite English sources when queries are in English, with this bias amplified for lower-resource languages and for documents positioned mid-context. Crucially, we find that models sometimes trade-off document relevance for language preference, indicating that citation choices are not always driven by informativeness alone. Our findings shed light on how language models leverage multilingual context and influence citation behavior.

Michael Browder, Kevin Duh, J. David Harris et al.

Scarcity of labeled training data remains the long pole in the tent for building performant language technology and generative AI models. Transformer models -- particularly LLMs -- are increasingly being used to mitigate the data scarcity problem via synthetic data generation. However, because the models are black boxes, the properties of the synthetic data are difficult to predict. In practice it is common for language technology engineers to 'fiddle' with the LLM temperature setting and hope that what comes out the other end improves the downstream model. Faced with this uncertainty, here we propose Data Kernel Perspective Space (DKPS) to provide the foundation for mathematical analysis yielding concrete statistical guarantees for the quality of the outputs of transformer models. We first show the mathematical derivation of DKPS and how it provides performance guarantees. Next we show how DKPS performance guarantees can elucidate performance of a downstream task, such as neural machine translation models or LLMs trained using Contrastive Preference Optimization (CPO). Limitations of the current work and future research are also discussed.

Brian Thompson, Huda Khayrallah, Antonios Anastasopoulos et al.

To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component's contribution to, and capacity for, domain adaptation. We find that freezing any single component during continued training has minimal impact on performance, and that performance is surprisingly good when a single component is adapted while holding the rest of the model fixed. We also find that continued training does not move the model very far from the out-of-domain model, compared to a sensitivity analysis metric, suggesting that the out-of-domain model can provide a good generic initialization for the new domain.

Jan Trmal, Gaurav Kumar, Vimal Manohar et al.

The paper summarizes the development of the LVCSR system built as a part of the Pashto speech-translation system at the SCALE (Summer Camp for Applied Language Exploration) 2015 workshop on "Speech-to-text-translation for low-resource languages". The Pashto language was chosen as a good "proxy" low-resource language, exhibiting multiple phenomena which make the speech-recognition and and speech-to-text-translation systems development hard. Even when the amount of data is seemingly sufficient, given the fact that the data originates from multiple sources, the preliminary experiments reveal that there is little to no benefit in merging (concatenating) the corpora and more elaborate ways of making use of all of the data must be worked out. This paper concentrates only on the LVCSR part and presents a range of different techniques that were found to be useful in order to benefit from multiple different corpora