Conversational Question Answering (ConvQA) involves multiple subtasks, i) to understand incomplete questions in their context, ii) to retrieve relevant information, and iii) to generate answers. This work presents PRAISE, a pipeline-based approach for ConvQA that trains LLM adapters for each of the three subtasks. As labeled training data for individual subtasks is unavailable in practice, PRAISE learns from its own generations using the final answering performance as feedback signal without human intervention and treats intermediate information, like relevant evidence, as weakly labeled data. We apply Direct Preference Optimization by contrasting successful and unsuccessful samples for each subtask. In our experiments, we show the effectiveness of this training paradigm: PRAISE shows improvements per subtask and achieves new state-of-the-art performance on a popular ConvQA benchmark, by gaining 15.5 percentage points increase in precision over baselines.
This paper explores SynTOD, a new synthetic data generation approach for developing end-to-end Task-Oriented Dialogue (TOD) Systems capable of handling complex tasks such as intent classification, slot filling, conversational question-answering, and retrieval-augmented response generation, without relying on crowdsourcing or real-world data. SynTOD utilizes a state transition graph to define the desired behavior of a TOD system and generates diverse, structured conversations through random walks and response simulation using large language models (LLMs). In our experiments, using graph-guided response simulations leads to significant improvements in intent classification, slot filling and response relevance compared to naive single-prompt simulated conversations. We also investigate the end-to-end TOD effectiveness of different base and instruction-tuned LLMs, with and without the constructed synthetic conversations. Finally, we explore how various LLMs can evaluate responses in a TOD system and how well they are correlated with human judgments. Our findings pave the path towards quick development and evaluation of domain-specific TOD systems. We release our datasets, models, and code for research purposes.
Efficiently modeling historical information is a critical component in addressing user queries within a conversational question-answering (QA) context, as historical context plays a vital role in clarifying the user's questions. However, irrelevant history induces noise in the reasoning process, especially for those questions with a considerable historical context. In our novel model-agnostic approach, referred to as CoTaH (Consistency-Trained augmented History), we augment the historical information with synthetic questions and subsequently employ consistency training to train a model that utilizes both real and augmented historical data to implicitly make the reasoning robust to irrelevant history. To the best of our knowledge, this is the first instance of research using question generation as a form of data augmentation to model conversational QA settings. By citing a common modeling error prevalent in previous research, we introduce a new baseline model and compare our model's performance against it, demonstrating an improvement in results, particularly when dealing with questions that include a substantial amount of historical context. The source code can be found on our GitHub page.
Open Retrieval Conversational Question Answering (OrConvQA) answers a question given a conversation as context and a document collection. A typical OrConvQA pipeline consists of three modules: a Retriever to retrieve relevant documents from the collection, a Reranker to rerank them given the question and the context, and a Reader to extract an answer span. The conversational turns can provide valuable context to answer the final query. State-of-the-art OrConvQA systems use the same history modeling for all three modules of the pipeline. We hypothesize this as suboptimal. Specifically, we argue that a broader context is needed in the first modules of the pipeline to not miss relevant documents, while a narrower context is needed in the last modules to identify the exact answer span. We propose NORMY, the first unsupervised non-uniform history modeling pipeline which generates the best conversational history for each module. We further propose a novel Retriever for NORMY, which employs keyphrase extraction on the conversation history, and leverages passages retrieved in previous turns as additional context. We also created a new dataset for OrConvQA, by expanding the doc2dial dataset. We implemented various state-of-the-art history modeling techniques and comprehensively evaluated them separately for each module of the pipeline on three datasets: OR-QUAC, our doc2dial extension, and ConvMix. Our extensive experiments show that NORMY outperforms the state-of-the-art in the individual modules and in the end-to-end system.
Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations about facts stored within a knowledge graph, dialogue utterances are transformed into graph queries in a process that is called knowledge-based conversational question answering. This paper evaluates the performance of large language models that have not been explicitly pre-trained on this task. Through a series of experiments on an extensive benchmark dataset, we compare models of varying sizes with different prompting techniques and identify common issue types in the generated output. Our results demonstrate that large language models are capable of generating graph queries from dialogues, with significant improvements achievable through few-shot prompting and fine-tuning techniques, especially for smaller models that exhibit lower zero-shot performance.
Humans seek information regarding a specific topic through performing a conversation containing a series of questions and answers. In the pursuit of conversational question answering research, we introduce the PCoQA, the first \textbf{P}ersian \textbf{Co}nversational \textbf{Q}uestion \textbf{A}nswering dataset, a resource comprising information-seeking dialogs encompassing a total of 9,026 contextually-driven questions. Each dialog involves a questioner, a responder, and a document from the Wikipedia; The questioner asks several inter-connected questions from the text and the responder provides a span of the document as the answer for each question. PCoQA is designed to present novel challenges compared to previous question answering datasets including having more open-ended non-factual answers, longer answers, and fewer lexical overlaps. This paper not only presents the comprehensive PCoQA dataset but also reports the performance of various benchmark models. Our models include baseline models and pre-trained models, which are leveraged to boost the performance of the model. The dataset and benchmarks are available at our Github page.
Conversational question-answering (CQA) systems aim to create interactive search systems that effectively retrieve information by interacting with users. To replicate human-to-human conversations, existing work uses human annotators to play the roles of the questioner (student) and the answerer (teacher). Despite its effectiveness, challenges exist as human annotation is time-consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of large language models (LLMs) in CQA simulation, we propose a simulation framework that employs zero-shot learner LLMs for simulating teacher-student interactions. Our framework involves two LLMs interacting on a specific topic, with the first LLM acting as a student, generating questions to explore a given search topic. The second LLM plays the role of a teacher by answering questions and is equipped with additional information, including a text on the given topic. We implement both the student and teacher by zero-shot prompting the GPT-4 model. To assess the effectiveness of LLMs in simulating CQA interactions and understand the disparities between LLM- and human-generated conversations, we evaluate the simulated data from various perspectives. We begin by evaluating the teacher's performance through both automatic and human assessment. Next, we evaluate the performance of the student, analyzing and comparing the disparities between questions generated by the LLM and those generated by humans. Furthermore, we conduct extensive analyses to thoroughly examine the LLM performance by benchmarking state-of-the-art reading comprehension models on both datasets. Our results reveal that the teacher LLM generates lengthier answers that tend to be more accurate and complete. The student LLM generates more diverse questions, covering more aspects of a given topic.
In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer. In this paper, we are interested in the robustness of a QR system to questions varying in rewriting hardness or difficulty. Since there is a lack of questions classified based on their rewriting hardness, we first propose a heuristic method to automatically classify questions into subsets of varying hardness, by measuring the discrepancy between a question and its rewrite. To find out what makes questions hard or easy for rewriting, we then conduct a human evaluation to annotate the rewriting hardness of questions. Finally, to enhance the robustness of QR systems to questions of varying hardness, we propose a novel learning framework for QR that first trains a QR model independently on each subset of questions of a certain level of hardness, then combines these QR models as one joint model for inference. Experimental results on two datasets show that our framework improves the overall performance compared to the baselines.
Large Multimodal Models (LMMs) extend Large Language Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses. Recently, region-level LMMs have been used to generate visually grounded responses. However, they are limited to only referring to a single object category at a time, require users to specify the regions, or cannot offer dense pixel-wise object grounding. In this work, we present Grounding LMM (GLaMM), the first model that can generate natural language responses seamlessly intertwined with corresponding object segmentation masks. GLaMM not only grounds objects appearing in the conversations but is flexible enough to accept both textual and optional visual prompts (region of interest) as input. This empowers users to interact with the model at various levels of granularity, both in textual and visual domains. Due to the lack of standard benchmarks for the novel setting of visually Grounded Conversation Generation (GCG), we introduce a comprehensive evaluation protocol with our curated grounded conversations. Our proposed GCG task requires densely grounded concepts in natural scenes at a large-scale. To this end, we propose a densely annotated Grounding-anything Dataset (GranD) using our proposed automated annotation pipeline that encompasses 7.5M unique concepts grounded in a total of 810M regions available with segmentation masks. Besides GCG, GLaMM also performs effectively on several downstream tasks, e.g., referring expression segmentation, image and region-level captioning and vision-language conversations.
The ability to handle miscommunication is crucial to robust and faithful conversational AI. People usually deal with miscommunication immediately as they detect it, using highly systematic interactional mechanisms called repair. One important type of repair is Third Position Repair (TPR) whereby a speaker is initially misunderstood but then corrects the misunderstanding as it becomes apparent after the addressee's erroneous response. Here, we collect and publicly release Repair-QA, the first large dataset of TPRs in a conversational question answering (QA) setting. The data is comprised of the TPR turns, corresponding dialogue contexts, and candidate repairs of the original turn for execution of TPRs. We demonstrate the usefulness of the data by training and evaluating strong baseline models for executing TPRs. For stand-alone TPR execution, we perform both automatic and human evaluations on a fine-tuned T5 model, as well as OpenAI's GPT-3 LLMs. Additionally, we extrinsically evaluate the LLMs' TPR processing capabilities in the downstream conversational QA task. The results indicate poor out-of-the-box performance on TPR's by the GPT-3 models, which then significantly improves when exposed to Repair-QA.
Although large language models (LLMs) has shown great performance on natural language processing (NLP) in the financial domain, there are no publicly available financial tailtored LLMs, instruction tuning datasets, and evaluation benchmarks, which is critical for continually pushing forward the open-source development of financial artificial intelligence (AI). This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation benchmark with 5 tasks and 9 datasets. We first construct the large-scale multi-task instruction data considering a variety of financial tasks, financial document types, and financial data modalities. We then propose a financial LLM called FinMA by fine-tuning LLaMA with the constructed dataset to be able to follow instructions for various financial tasks. To support the evaluation of financial LLMs, we propose a standardized benchmark that covers a set of critical financial tasks, including five financial NLP tasks and one financial prediction task. With this benchmark, we conduct a detailed analysis of FinMA and several existing LLMs, uncovering their strengths and weaknesses in handling critical financial tasks. The model, datasets, benchmark, and experimental results are open-sourced to facilitate future research in financial AI.
Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation based on a retriever-reader pipeline, which retrieves passages and then predicts answers with them. However, such a pipeline approach not only makes the reader vulnerable to the errors propagated from the retriever, but also demands additional effort to develop both the retriever and the reader, which further makes it slower since they are not runnable in parallel. In this work, we propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words, reducing the conventional two distinct subtasks into a single one. Also, for the first time, we study its capability for ODConvQA tasks. However, simply adopting it is largely problematic, due to the dependencies between previous and current turns in a conversation. To address this problem, we further introduce a novel contrastive learning strategy, making sure to reflect previous turns when retrieving the phrase for the current context, by maximizing representational similarities of consecutive turns in a conversation while minimizing irrelevant conversational contexts. We validate our model on two ODConvQA datasets, whose experimental results show that it substantially outperforms the relevant baselines with the retriever-reader. Code is available at: https://github.com/starsuzi/PRO-ConvQA.
Temperature sampling is a conventional approach to diversify large language model predictions. As temperature increases, the prediction becomes diverse but also vulnerable to hallucinations -- generating tokens that are sensible but not factual. One common approach to mitigate hallucinations is to provide source/grounding documents and the model is trained to produce predictions that bind to and are attributable to the provided source. It appears that there is a trade-off between diversity and attribution. To mitigate any such trade-off, we propose to relax the constraint of having a fixed temperature over decoding steps, and a mechanism to guide the dynamic temperature according to its relevance to the source through KL-divergence. Our experiments justifies the trade-off, and shows that our sampling algorithm outperforms the conventional top-k and top-p algorithms in conversational question-answering and summarization tasks.
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care. Despite the success of large language models (LLMs) in complex reasoning tasks in various fields, such as mathematics, logic, and commonsense QA, they still need to improve with the increased complexity and specialization of the medical field. This is because medical CQA tasks require not only strong medical reasoning, but also the ability to think broadly and deeply. In this paper, to address these challenges in medical CQA tasks that need to be considered and understood in many aspects, we propose the Holistically Thought (HoT) method, which is designed to guide the LLMs to perform the diffused and focused thinking for generating high-quality medical responses. The proposed HoT method has been evaluated through automated and manual assessments in three different medical CQA datasets containing the English and Chinese languages. The extensive experimental results show that our method can produce more correctness, professional, and considerate answers than several state-of-the-art (SOTA) methods, manifesting its effectiveness. Our code in https://github.com/WENGSYX/HoT.
Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. To apply such models to a real-world scenario, some existing work uses predicted answers, instead of unavailable ground-truth answers, as the conversation history for inference. However, since these models usually predict wrong answers, using all the predictions without filtering significantly hampers the model performance. To address this problem, we propose to filter out inaccurate answers in the conversation history based on their estimated confidences and uncertainties from the ConvQA model, without making any architectural changes. Moreover, to make the confidence and uncertainty values more reliable, we propose to further calibrate them, thereby smoothing the model predictions. We validate our models, Answer Selection-based realistic Conversation Question Answering, on two standard ConvQA datasets, and the results show that our models significantly outperform relevant baselines. Code is available at: https://github.com/starsuzi/AS-ConvQA.
In this paper, we are interested in developing semantic parsers which understand natural language questions embedded in a conversation with a user and ground them to formal queries over definitions in a general purpose knowledge graph (KG) with very large vocabularies (covering thousands of concept names and relations, and millions of entities). To this end, we develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof. We present two different semantic parsing approaches and highlight the challenges of the task: dealing with large vocabularies, modelling conversation context, predicting queries with multiple entities, and generalising to new questions at test time. We hope our dataset will serve as useful testbed for the development of conversational semantic parsers. Our dataset and models are released at https://github.com/EdinburghNLP/SPICE.
Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions: deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~ 50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.
In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv. There are three modules in QKConv: a query generator, an off-the-shelf knowledge selector, and a response generator. QKConv is optimized through joint training, which produces the response by exploring multiple candidate queries and leveraging corresponding selected knowledge. The joint training solely relies on the dialogue context and target response, getting exempt from extra query annotations or knowledge provenances. To evaluate the effectiveness of the proposed QKConv, we conduct experiments on three representative knowledge-intensive conversation datasets: conversational question-answering, task-oriented dialogue, and knowledge-grounded conversation. Experimental results reveal that QKConv performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.
Long-form numerical reasoning in financial analysis aims to generate a reasoning program to calculate the correct answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numbers. Meanwhile, the program consistency were ignored under supervised training, resulting in lower training accuracy and diversity. To solve these problems, we proposed APOLLO to improve the long-form numerical reasoning framework. For the retriever, we adopt a number-aware negative sampling strategy to enable the retriever to be more discriminative on key numerical facts. For the generator, we design consistency-based reinforcement learning and target program augmentation strategy based on the consistency of program execution results. Experimental results on the FinQA and ConvFinQA leaderboard verify the effectiveness of our proposed method, achieving the new state-of-the-art.
Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate passages from a large corpus and the latter requires better understanding of a question with contexts to predict the answers. This paper proposes ConvADR-QA that leverages historical answers to boost retrieval performance and further achieves better answering performance. In our proposed framework, the retrievers use a teacher-student framework to reduce noises from previous turns. Our experiments on the benchmark dataset, OR-QuAC, demonstrate that our model outperforms existing baselines in both extractive and generative reader settings, well justifying the effectiveness of historical answers for open-domain conversational question answering.