Mihir Parmar, Nisarg Patel, Neeraj Varshney, Mutsumi Nakamura, Man Luo, Santosh Mashetty, Arindam Mitra, Chitta Baral. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Nemika Tyagi, Mihir Parmar, Mohith Kulkarni, Aswin Rrv, Nisarg Patel, Mutsumi Nakamura, Arindam Mitra, Chitta Baral. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Large language models (LLMs) frequently hallucinate on abstractive summarization tasks such as document-based question-answering, meeting summarization, and clinical report generation, even though all necessary information is included in context. However, optimizing to make LLMs hallucinate less is challenging, as hallucination is hard to efficiently, cheaply, and reliably evaluate at each optimization step. In this work, we show that reducing hallucination on a _synthetic task_ can also reduce hallucination on real-world downstream tasks. Our method, SynTra, first designs a synthetic task where hallucinations are easy to elicit and measure. It next optimizes the LLM's system message via prefix tuning on the synthetic task, then uses the system message on realistic, hard-to-optimize tasks. Across three realistic abstractive summarization tasks, we reduce hallucination for two 13B-parameter LLMs using supervision signal from only a synthetic retrieval task. We also find that optimizing the system message rather than the model weights can be critical; fine-tuning the entire model on the synthetic task can counterintuitively _increase_ hallucination. Overall, SynTra demonstrates that the extra flexibility of working with synthetic data can help mitigate undesired behaviors in practice.

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and sources of scientific knowledge may evolve rapidly. Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain. In this paper, we seek to improve information retrieval (IR) using neural retrievers (NR) in the biomedical domain, and achieve this goal using a three-pronged approach. First, to tackle the relative lack of data in the biomedical domain, we propose a template-based question generation method that can be leveraged to train neural retriever models. Second, we develop two novel pre-training tasks that are closely aligned to the downstream task of information retrieval. Third, we introduce the ``Poly-DPR'' model which encodes each context into multiple context vectors. Extensive experiments and analysis on the BioASQ challenge suggest that our proposed method leads to large gains over existing neural approaches and beats BM25 in the small-corpus setting. We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.

Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Natural Language Inference (NLI) plays an important role in many natural language processing tasks such as question answering. However, existing NLI modules that are trained on existing NLI datasets have several drawbacks. For example, they do not capture the notion of entity and role well and often end up making mistakes such as “Peter signed a deal” can be inferred from “John signed a deal”. As part of this work, we have developed two datasets that help mitigate such issues and make the systems better at understanding the notion of “entities” and “roles”. After training the existing models on the new dataset we observe that the existing models do not perform well on one of the new benchmark. We then propose a modification to the “word-to-word” attention function which has been uniformly reused across several popular NLI architectures. The resulting models perform as well as their unmodified counterparts on the existing benchmarks and perform significantly well on the new benchmarks that emphasize “roles” and “entities”.

While in recent years machine learning (ML) based approaches have been the popular approach in developing endto-end question answering systems, such systems often struggle when additional knowledge is needed to correctly answer the questions. Proposed alternatives involve translating the question and the natural language text to a logical representation and then use logical reasoning. However, this alternative falters when the size of the text gets bigger. To address this we propose an approach that does logical reasoning over premises written in natural language text. The proposed method uses recent features of Answer Set Programming (ASP) to call external NLP modules (which may be based on ML) which perform simple textual entailment. To test our approach we develop a corpus based on the life cycle questions and showed that Our system achieves up to 18% performance gain when compared to standard MCQ solvers.

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA that focus on linguistic understanding, OpenBookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.

Winograd Schema Challenge (WSC) is a pronoun resolution task which seems to require reasoning with commonsense knowledge.The needed knowledge is not present in the given text.Automatic extraction of the needed knowledge is a bottleneck in solving the challenge.The existing state-of-the-art approach uses the knowledge embedded in their pretrained language model.However, the language models only embed part of the knowledge, the ones related to frequently co-existing concepts.This limits the performance of such models on the WSC problems.In this work, we build-up on the language model based methods and augment them with a commonsense knowledge hunting (using automatic extraction from text) module and an explicit reasoning module.Our end-to-end system built in such a manner improves on the accuracy of two of the available language model based approaches by 5.53% and 7.7% respectively.Overall our system achieves the state-of-theart accuracy of 71.06% on the WSC dataset, an improvement of 7.36% over the previous best.

Abstract Over the years the Artificial Intelligence (AI) community has produced several datasets which have given the machine learning algorithms the opportunity to learn various skills across various domains. However, a subclass of these machine learning algorithms that aimed at learning logic programs, namely the Inductive Logic Programming algorithms, have often failed at the task due to the vastness of these datasets. This has impacted the usability of knowledge representation and reasoning techniques in the development of AI systems. In this research, we try to address this scalability issue for the algorithms that learn answer set programs. We present a sound and complete algorithm which takes the input in a slightly different manner and performs an efficient and more user controlled search for a solution. We show via experiments that our algorithm can learn from two popular datasets from machine learning community, namely bAbl (a question answering dataset) and MNIST (a dataset for handwritten digit recognition), which to the best of our knowledge was not previously possible. The system is publicly available at https://goo.gl/KdWAcV .

A group of researchers from Facebook has recently proposed a set of 20 question-answering tasks (Facebook's bAbl dataset) as a challenge for the natural language understanding ability of an intelligent agent. These tasks are designed to measure various skills of an agent, such as: fact based question-answering, simple induction, the ability to find paths, co-reference resolution and many more. Their goal is to aid in the development of systems that can learn to solve such tasks and to allow a proper evaluation of such systems. They show existing systems cannot fully solve many of those toy tasks. In this work, we present a system that excels at all the tasks except one. The proposed model of the agent uses the Answer Set Programming (ASP) language as the primary knowledge representation and reasoning language along with the standard statistical Natural Language Processing (NLP) models. Given a training dataset containing a set of narrations, questions and their answers, the agent jointly uses a translation system, an Inductive Logic Programming algorithm and Statistical NLP methods to learn the knowledge needed to answer similar questions. Our results demonstrate that the introduction of a reasoning module significantly improves the performance of an intelligent agent.

Solving simple arithmetic word problems is one of the challenges in Natural Language Understanding.This paper presents a novel method to learn to use formulas to solve simple arithmetic word problems.Our system, analyzes each of the sentences to identify the variables and their attributes; and automatically maps this information into a higher level representation.It then uses that representation to recognize the presence of a formula along with its associated variables.An equation is then generated from the formal description of the formula.In the training phase, it learns to score the pair from the systematically generated higher level representation.It is able to solve 86.07% of the problems in a corpus of standard primary school test questions and beats the state-of-the-art by a margin of 8.07%.

Nguyen Vo, Arindam Mitra, Chitta Baral. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Logic grid puzzle is a genre of logic puzzles in which we are given (in a natural language) a scenario, the object to be deduced and certain clues.The reader has to figure out the solution using the clues provided and some generic domain constraints.In this paper, we present a system, LOGICIA, that takes a logic grid puzzle and the set of elements in the puzzle and tries to solve it by translating it to the knowledge representation and reasoning language of Answer Set Programming (ASP) and then using an ASP solver.The translation to ASP involves extraction of entities and their relations from the clues.For that we use a novel learning based approach which uses varied supervision, including the entities present in a clue and the expected representation of a clue in ASP.Our system, LO-GICIA, learns to automatically translate a clue with 81.11% accuracy and is able to solve 71% of the problems of a corpus.This is the first learning system that can solve logic grid puzzles described in natural language in a fully automated manner.The code and the data will be made publicly available at http://bioai.lab.asu.edu/logicgridpuzzles.

Epidemic protocols such as gossip have proven to have many desirable properties for information sharing. However, trust is one of the issues that is yet to be examined with respect to these protocols. In this paper, we present a trusted gossip protocol that uses trust estimates to impede spreading of rumors with reasonable message and processing overheads. We use traces collected from known social networks to estimate the performance of trusted gossip.

In a recent study, we proposed a trusted gossip protocol for rumor resistant information sharing in peer-to-peer networks. While trust aware gossiping significantly reduced the rumor spread on the network, we observed that the random message spraying in trusted gossip creates too many redundant messages increasing the message overhead and error rate. In this paper, we propose a message targeting scheme that can significantly improve the performance of the trusted gossip. Our targeting scheme can be easily implemented in a social network setting. We performed large-scale simulations using traces collected from the Flickr social network and other data sets to estimate the performance of targeting in trusted gossip. Our experiments show that significant performance gains can be achieved.

Trust and security are two major issues in large distributed systems that are highly inter-dependent such that it is hard to bootstrap one without the other. In distributed systems that are built using private resources, security is bootstrapped using off-line trust relationships. Mandating off-line trust relations, however, has the undesirable effect of limiting the membership of distributed systems. Therefore, public-resource based systems need online trust modeling. This paper presents a two-layered framework that considers trust, security and incentives in an integrated fashion. Our framework is characterized by (a) a community-based process that is essentially decentralized for evaluating and assigning trust for peers (b) policy autonomy in administering incentives and trust, and (c) lowers the join time trust requirements for peers. Results from early prototyping and simulations show the proposed framework can be implemented with acceptable overheads and is capable of evolving trust and applying it for resource management.

This work describes a design for a quality of service aware public computing utility (PCU). The goal of the PCU is to utilize the idle capacity of the shared public resources and augment the capacity with dedicated resources as necessary, to provide high quality of service to the clients at the least cost. Our PCU design combines peer-to-peer (P2P) and grid computing ideas in a novel manner to construct a utility-based computing environment. In This work, we present the overall architecture and describe two major components: a P2P overlay substrate for connecting the resources in a global network and a community-based decentralized resource management system.