Retrieval-augmented generation has gained popularity as a framework to enhance large language models with external knowledge. However, its effectiveness hinges on the retrieval robustness of the model. If the model lacks retrieval robustness, its performance is constrained by the accuracy of the retriever, resulting in significant compromises when the retrieved context is irrelevant. In this paper, we evaluate the “implicit” retrieval robustness of various large language models, instructing them to directly output the final answer without explicitly judging the relevance of the retrieved context. Our findings reveal that fine-tuning on a mix of gold and distracting context significantly enhances the model’s robustness to retrieval inaccuracies, while still maintaining its ability to extract correct answers when retrieval is accurate. This suggests that large language models can implicitly handle relevant or irrelevant retrieved context by learning solely from the supervision of the final answer in an end-to-end manner. Introducing an additional process for explicit relevance judgment can be unnecessary and disrupts the end-to-end approach.

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users’ contextual search intent when generating responses is an understudied topic for conversational question answering (QA). This conversational extension leads to additional concerns when compared to single-turn QA as it is more challenging for systems to comprehend conversational context and manage retrieved passages over multiple turns. In this work, we propose a method for enabling LLMs to decide when to retrieve in RAG settings given a conversational context. When retrieval is deemed necessary, the LLM then rewrites the conversation for passage retrieval and judges the relevance of returned passages before response generation. Operationally, we build on the single-turn SELF-RAG framework (Asai et al., 2023) and propose SELF-multi-RAG for conversational settings. SELF-multi-RAG demonstrates improved capabilities over single-turn variants with respect to retrieving relevant passages (by using summarized conversational context) and assessing the quality of generated responses. Experiments on three conversational QA datasets validate the enhanced response generation capabilities of SELF-multi-RAG with improvements of ~13% measured by human annotation.

Recent years have witnessed the thriving of pretrained Transformer-based language models for understanding semi-structured tables, with several applications, such as Table Question Answering (TableQA).These models are typically trained on joint tables and surrounding natural language text, by linearizing table content into sequences comprising special tokens and cell information. This yields very long sequences which increase system inefficiency, and moreover, simply truncating long sequences results in information loss for downstream tasks. We propose Inner Table Retriever (ITR), a general-purpose approach for handling long tables in TableQA that extracts sub-tables to preserve the most relevant information for a question. We show that ITR can be easily integrated into existing systems to improve their accuracy with up to 1.3-4.8% and achieve state-of-the-art results in two benchmarks, i.e., 63.4% in WikiTableQuestions and 92.1% in WikiSQL. Additionally, we show that ITR makes TableQA systems more robust to reduced model capacity and to different ordering of columns and rows. We make our code available at: https://github.com/amazon-science/robust-tableqa.

Recent open-domain TableQA models are typically implemented as retriever-reader pipelines. The retriever component is usually a variant of the Dense Passage Retriever, which computes the similarities between questions and tables based on a single representation of each. These fixed vectors can be insufficient to capture fine-grained features of potentially very big tables with heterogeneous row/column information. We address this limitation by 1) applying late interaction models which enforce a finer-grained interaction between question and table embeddings at retrieval time. In addition, we 2) incorporate a joint training scheme of the retriever and reader with explicit table-level signals, and 3) embed a binary relevance token as a prefix to the answer generated by the reader, so we can determine at inference time whether the table used to answer the question is reliable and filter accordingly. The combined strategies set a new state-to-the-art performance on two public open-domain TableQA datasets.

In this paper, we present an evaluation of sentence representation models on the paraphrase detection task. The evaluation is designed to simulate a real-world problem of plagiarism and is based on one of the most important cases of forgery in modern history: the so-called “Protocols of the Elders of Zion”. The sentence pairs for the evaluation are taken from the infamous forged text “Protocols of the Elders of Zion” (Protocols) by unknown authors; and by “Dialogue in Hell between Machiavelli and Montesquieu” by Maurice Joly. Scholars have demonstrated that the first text plagiarizes from the second, indicating all the forged parts on qualitative grounds. Following this evidence, we organized the rephrased texts and asked native speakers to quantify the level of similarity between each pair. We used this material to evaluate sentence representation models in two languages: English and French, and on three tasks: similarity correlation, paraphrase identification, and paraphrase retrieval. Our evaluation aims at encouraging the development of benchmarks based on real-world problems, as a means to prevent problems connected to AI hypes, and to use NLP technologies for social good. Through our evaluation, we are able to confirm that the infamous Protocols are actually a plagiarized text but, as we will show, we encounter several problems connected with the convoluted nature of the task, that is very different from the one reported in standard benchmarks of paraphrase detection and sentence similarity. Code and data available at https://github.com/roccotrip/protocols.

The recent advent of modern pretrained language models has sparked a revolution in Natural Language Processing (NLP), especially in multilingual and cross-lingual applications. Today, such language models have become the de facto standard for providing rich input representations to neural systems, achieving unprecedented results in an increasing range of benchmarks. However, questions that often arise are: firstly, whether current language models are, indeed, able to capture explicit, symbolic meaning; secondly, if they are, to what extent; thirdly, and perhaps more importantly, whether current approaches are capable of scaling across languages. In this cutting-edge tutorial, we will review recent efforts that have aimed at shedding light on meaning in NLP, with a focus on three key open problems in lexical and sentence-level semantics: Word Sense Disambiguation, Semantic Role Labeling, and Semantic Parsing. After a brief introduction, we will spotlight how state-of-the-art models tackle these tasks in multiple languages, showing where they excel and where they fail. We hope that this tutorial will broaden the audience interested in multilingual semantics and inspire researchers to further advance the field.

With the advent of contextualized embeddings, attention towards neural ranking approaches for Information Retrieval increased considerably. However, two aspects have remained largely neglected: i) queries usually consist of few keywords only, which increases ambiguity and makes their contextualization harder, and ii) performing neural ranking on non-English documents is still cumbersome due to shortage of labeled datasets. In this paper we present SIR (Sense-enhanced Information Retrieval) to mitigate both problems by leveraging word sense information. At the core of our approach lies a novel multilingual query expansion mechanism based on Word Sense Disambiguation that provides sense definitions as additional semantic information for the query. Importantly, we use senses as a bridge across languages, thus allowing our model to perform considerably better than its supervised and unsupervised alternatives across French, German, Italian and Spanish languages on several CLEF benchmarks, while being trained on English Robust04 data only. We release SIR at https://github.com/SapienzaNLP/sir.

In this paper we present SPRING Online Services, a Web interface and RESTful APIs for our state-of-the-art AMR parsing and generation system, SPRING (Symmetric PaRsIng aNd Generation). The Web interface has been developed to be easily used by the Natural Language Processing community, as well as by the general public. It provides, among other things, a highly interactive visualization platform and a feedback mechanism to obtain user suggestions for further improvements of the system’s output. Moreover, our RESTful APIs enable easy integration of SPRING in downstream applications where AMR structures are needed. Finally, we make SPRING Online Services freely available at http://nlp.uniroma1.it/spring and, in addition, we release extra model checkpoints to be used with the original SPRING Python code.

Abstract Meaning Representation (AMR) is a popular formalism of natural language that represents the meaning of a sentence as a semantic graph. It is agnostic about how to derive meanings from strings and for this reason it lends itself well to the encoding of semantics across languages. However, cross-lingual AMR parsing is a hard task, because training data are scarce in languages other than English and the existing English AMR parsers are not directly suited to being used in a cross-lingual setting. In this work we tackle these two problems so as to enable cross-lingual AMR parsing: we explore different transfer learning techniques for producing automatic AMR annotations across languages and develop a cross-lingual AMR parser, XL-AMR. This can be trained on the produced data and does not rely on AMR aligners or source-copy mechanisms as is commonly the case in English AMR parsing. The results of XL-AMR significantly surpass those previously reported in Chinese, German, Italian and Spanish. Finally we provide a qualitative analysis which sheds light on the suitability of AMR across languages. We release XL-AMR at github.com/SapienzaNLP/xl-amr.