Xiangci Li

Manan Suri, Xiangci Li, Mehdi Shojaie et al. · amazon-science

Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such underspecified requests are highly correlated with longer trajectories involving either over-exploration or repeated attempts at applying the same fix without proper evolution or testing, leading to suboptimal outcomes across software development tasks. We introduce CodeScout, a contextual query refinement approach that systematically converts underspecified user requests into comprehensive, actionable problem statements through lightweight pre-exploration of the target codebase. Our key innovation is demonstrating that structured analysis before task execution can supplement existing agentic capabilities without requiring any modifications to their underlying scaffolds. CodeScout performs targeted context scoping, conducts multi-perspective analysis examining potential fixes and exploration opportunities, then synthesizes these insights into enhanced problem statements with reproduction steps, expected behaviors, and targeted exploration hints. This pre-exploration directly addresses the identified failure patterns by reducing non-converging agent trajectories while clarifying user intent in natural language space. We evaluate CodeScout using state-of-the-art agentic scaffolds and language models on SWEBench-Verified, demonstrating a 20\% improvement in resolution rates with up to 27 additional issues resolved compared to the default baseline method. Our results suggest that systematic query refinement through contextual analysis represents a promising direction for enhancing AI code assistance capabilities.

Xiangci Li, Biswadip Mandal, Jessica Ouyang

Academic research is an exploratory activity to discover new solutions to problems. By this nature, academic research works perform literature reviews to distinguish their novelties from prior work. In natural language processing, this literature review is usually conducted under the "Related Work" section. The task of related work generation aims to automatically generate the related work section given the rest of the research paper and a list of papers to cite. Prior work on this task has focused on the sentence as the basic unit of generation, neglecting the fact that related work sections consist of variable length text fragments derived from different information sources. As a first step toward a linguistically-motivated related work generation framework, we present a Citation Oriented Related Work Annotation (CORWA) dataset that labels different types of citation text fragments from different information sources. We train a strong baseline model that automatically tags the CORWA labels on massive unlabeled related work section texts. We further suggest a novel framework for human-in-the-loop, iterative, abstractive related work generation.

Xiangci Li, Yi-Hui Lee, Jessica Ouyang

An automatic citation generation system aims to concisely and accurately describe the relationship between two scientific articles. To do so, such a system must ground its outputs to the content of the cited paper to avoid non-factual hallucinations. Due to the length of scientific documents, existing abstractive approaches have conditioned only on cited paper abstracts. We demonstrate empirically that the abstract is not always the most appropriate input for citation generation and that models trained in this way learn to hallucinate. We propose to condition instead on the cited text span (CTS) as an alternative to the abstract. Because manual CTS annotation is extremely time- and labor-intensive, we experiment with distant labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations in model training, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.

Biswadip Mandal, Xiangci Li, Jessica Ouyang

A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length.

Xiangci Li, Jessica Ouyang

To convince readers of the novelty of their research paper, authors must perform a literature review and compose a coherent story that connects and relates prior works to the current work. This challenging nature of literature review writing makes automatic related work generation (RWG) academically and computationally interesting, and also makes it an excellent test bed for examining the capability of SOTA natural language processing (NLP) models. Since the initial proposal of the RWG task, its popularity has waxed and waned, following the capabilities of mainstream NLP approaches. In this work, we survey the zoo of RWG historical works, summarizing the key approaches and task definitions and discussing the ongoing challenges of RWG.

Xiangci Li, Zhiyu Chen, Jason Ingyu Choi et al.

The goal of conversational product search (CPS) is to develop an intelligent, chat-based shopping assistant that can directly interact with customers to understand shopping intents, ask clarification questions, and find relevant products. However, training such assistants is hindered mainly due to the lack of reliable and large-scale datasets. Prior human-annotated CPS datasets are extremely small in size and lack integration with real-world product search systems. We propose a novel approach, TRACER, which leverages large language models (LLMs) to generate realistic and natural conversations for different shopping domains. TRACER's novelty lies in grounding the generation to dialogue plans, which are product search trajectories predicted from a decision tree model, that guarantees relevant product discovery in the shortest number of search conditions. We also release the first target-oriented CPS dataset Wizard of Shopping (WoS), containing highly natural and coherent conversations (3.6k) from three shopping domains. Finally, we demonstrate the quality and effectiveness of WoS via human evaluations and downstream tasks.

Biswadip Mandal, Xiangci Li, Jessica Ouyang

Abstractive citation text generation is usually framed as an infilling task, where a sequence-to-sequence model is trained to generate a citation given a reference paper and the context window around the target; the generated citation should be a brief discussion of the reference paper as it relates to the citing context. However, examining a recent LED-based citation generation system, we find that many of the generated citations are generic summaries of the reference papers main contribution, ignoring the citation contexts focus on a different topic. To address this problem, we propose a simple modification to the citation text generation task: the generation target is not only the citation itself, but the entire context window, including the target citation. This approach can be easily applied to any abstractive citation generation system, and our experimental results show that training in this way is preferred by human readers and allows the generation model to make use of contextual clues about what topic to discuss and what stance to take.

Xiangci Li, Jessica Ouyang

Due to the rapid pace of research publications, keeping up to date with all the latest related papers is very time-consuming, even with daily feed tools. There is a need for automatically generated, short, customized literature reviews of sets of papers to help researchers decide what to read. While several works in the last decade have addressed the task of explaining a single research paper, usually in the context of another paper citing it, the relationship among multiple papers has been ignored; prior works have focused on generating a single citation sentence in isolation, without addressing the expository and transition sentences needed to connect multiple papers in a coherent story. In this work, we explore a feature-based, LLM-prompting approach to generate richer citation texts, as well as generating multiple citations at once to capture the complex relationships among research papers. We perform an expert evaluation to investigate the impact of our proposed features on the quality of the generated paragraphs and find a strong correlation between human preference and integrative writing style, suggesting that humans prefer high-level, abstract citations, with transition sentences between them to provide an overall story.

Xiangci Li, Sihao Chen, Rajvi Kapadia et al.

Claim verification in real-world settings (e.g. against a large collection of candidate evidences retrieved from the web) typically requires identifying and aggregating a complete set of evidence pieces that collectively provide full support to the claim. The problem becomes particularly challenging when there exists distinct sets of evidence that could be used to verify the claim from different perspectives. In this paper, we formally define and study the problem of identifying such minimal evidence groups (MEGs) for claim verification. We show that MEG identification can be reduced from Set Cover problem, based on entailment inference of whether a given evidence group provides full/partial support to a claim. Our proposed approach achieves 18.4% and 34.8% absolute improvements on the WiCE and SciFact datasets over LLM prompting. Finally, we demonstrate the benefits of MEGs in downstream applications such as claim generation.

Xiangci Li, Linfeng Song, Lifeng Jin et al.

Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previously been shown to be useful as support knowledge. Even in the era of large language models, response generation grounded in knowledge retrieved from additional up-to-date sources remains a practically important approach. While prior work using single-source knowledge has shown a clear positive correlation between the performances of knowledge selection and response generation, there are no existing multi-source datasets for evaluating support knowledge retrieval. Further, prior work has assumed that the knowledge sources available at test time are the same as during training. This unrealistic assumption unnecessarily handicaps models, as new knowledge sources can become available after a model is trained. In this paper, we present a high-quality benchmark named multi-source Wizard of Wikipedia (Ms.WoW) for evaluating multi-source dialogue knowledge selection and response generation. Unlike existing datasets, it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. We further propose a new challenge, dialogue knowledge plug-and-play, which aims to test an already trained dialogue model on using new support knowledge from previously unseen sources in a zero-shot fashion.

Yi-Hui Lee, Xiangci Li, Jessica Ouyang

Recent large language models (LLMs) have demonstrated a remarkable ability to perform natural language understanding and generation tasks. In this work, we investigate the use of LLMs for evaluating faithfulness in news summarization, finding that it achieves a strong correlation with human judgments. We further investigate LLMs' capabilities as a faithfulness post-editor, experimenting with different chain-of-thought prompts for locating and correcting factual inconsistencies between a generated summary and the source news document and are able to achieve a higher editing success rate than was reported in prior work. We perform both automated and human evaluations of the post-edited summaries, finding that prompting LLMs using chain-of-thought reasoning about factual error types is an effective faithfulness post-editing strategy, performing comparably to fine-tuned post-editing models. We also demonstrate that multiple rounds of post-editing, which has not previously been explored, can be used to gradually improve the faithfulness of summaries whose errors cannot be fully corrected in a single round.

Xiangci Li, Jessica Ouyang

Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model's output. While prior work has demonstrated the importance of improving knowledge retrieval for boosting generation quality, the role of knowledge selection, a.k.a. reranking or filtering, remains less clear. This paper empirically analyzes how knowledge selection influences downstream generation performance in RAG systems. By simulating different retrieval and selection conditions through a controlled mixture of gold and distractor knowledge, we assess the impact of these factors on generation outcomes. Our findings indicate that the downstream generator model's capability, as well as the complexity of the task and dataset, significantly influence the impact of knowledge selection on the overall RAG system performance. In typical scenarios, improving the knowledge recall score is key to enhancing generation outcomes, with the knowledge selector providing limited benefit when a strong generator model is used on clear, well-defined tasks. For weaker generator models or more ambiguous tasks and datasets, the knowledge F1 score becomes a critical factor, and the knowledge selector plays a more prominent role in improving overall performance.

Xiangci Li, Jessica Ouyang

Academic research is an exploration activity to solve problems that have never been resolved before. By this nature, each academic research work is required to perform a literature review to distinguish its novelties that have not been addressed by prior works. In natural language processing, this literature review is usually conducted under the "Related Work" section. The task of automatic related work generation aims to automatically generate the "Related Work" section given the rest of the research paper and a list of cited papers. Although this task was proposed over 10 years ago, it received little attention until very recently, when it was cast as a variant of the scientific multi-document summarization problem. However, even today, the problems of automatic related work and citation text generation are not yet standardized. In this survey, we conduct a meta-study to compare the existing literature on related work generation from the perspectives of problem formulation, dataset collection, methodological approach, performance evaluation, and future prospects to provide the reader insight into the progress of the state-of-the-art studies, as well as and how future studies can be conducted. We also survey relevant fields of study that we suggest future work to consider integrating.

Kinjal Basu, Huaduo Wang, Nancy Dominguez et al.

We report on the design and development of the CASPR system, a socialbot designed to compete in the Amazon Alexa Socialbot Challenge 4. CASPR's distinguishing characteristic is that it will use automated commonsense reasoning to truly "understand" dialogs, allowing it to converse like a human. Three main requirements of a socialbot are that it should be able to "understand" users' utterances, possess a strategy for holding a conversation, and be able to learn new knowledge. We developed techniques such as conversational knowledge template (CKT) to approximate commonsense reasoning needed to hold a conversation on specific topics. We present the philosophy behind CASPR's design as well as details of its implementation. We also report on CASPR's performance as well as discuss lessons learned.

Xiangci Li, Gully Burns, Nanyun Peng

Even for domain experts, it is a non-trivial task to verify a scientific claim by providing supporting or refuting evidence rationales. The situation worsens as misinformation is proliferated on social media or news websites, manually or programmatically, at every moment. As a result, an automatic fact-verification tool becomes crucial for combating the spread of misinformation. In this work, we propose a novel, paragraph-level, multi-task learning model for the SciFact task by directly computing a sequence of contextualized sentence embeddings from a BERT model and jointly training the model on rationale selection and stance prediction.

Xiangci Li, Hairong Liu, Liang Huang

Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. Inspired by this, we address the stand-alone spelling correction problem, which only corrects the spelling of each token without additional token insertion or deletion, by utilizing both spelling information and global context representations. We present a simple yet powerful solution that jointly detects and corrects misspellings as a sequence labeling task by fine-turning a pre-trained language model. Our solution outperforms the previous state-of-the-art result by 12.8% absolute F0.5 score.

Xiangci Li, Gully Burns, Nanyun Peng

Evidence plays a crucial role in any biomedical research narrative, providing justification for some claims and refutation for others. We seek to build models of scientific argument using information extraction methods from full-text papers. We present the capability of automatically extracting text fragments from primary research papers that describe the evidence presented in that paper's figures, which arguably provides the raw material of any scientific argument made within the paper. We apply richly contextualized deep representation learning pre-trained on biomedical domain corpus to the analysis of scientific discourse structures and the extraction of "evidence fragments" (i.e., the text in the results section describing data presented in a specified subfigure) from a set of biomedical experimental research articles. We first demonstrate our state-of-the-art scientific discourse tagger on two scientific discourse tagging datasets and its transferability to new datasets. We then show the benefit of leveraging scientific discourse tags for downstream tasks such as claim-extraction and evidence fragment detection. Our work demonstrates the potential of using evidence fragments derived from figure spans for improving the quality of scientific claims by cataloging, indexing and reusing evidence fragments as independent documents.