LitPivot：在文献图景中通过动态情境化来发展研究想法

Back to Articles

📄 论文📄 Paper

读到一篇新论文可能会改变研究思路的发展方向。研究者可能会发现，已经有人解决了自己提出的贡献所针对的问题；也可能在论文中发现一个尚未解决的问题，从而受到启发，探索新的研究方向。Encountering a new paper can change a research idea's trajectory. The researcher may discover that someone has already addressed their proposed contribution, or find an unresolved problem in the paper that inspires a new direction of inquiry.

我们将这一过程称为“文献驱动的转向”：即因阅读既有研究而改变研究方向。它将研究者往往需要分别处理的两项工作联系起来：构思研究想法，以及决定以哪些文献作为参照来评估这一想法。We call this process a literature-initiated pivot: a change in research direction prompted by reading prior work. It connects two activities that researchers often have to manage separately: developing an idea and deciding which literature to measure it against.

我们与宾夕法尼亚大学的合作者共同开发了 LitPivot，这是一个帮助研究人员应对这些转向的系统。LitPivot 利用通过 Asta Paper Finder 检索到的论文，围绕正在编辑的提案部分整理相关文献，提供有选定研究摘录作为依据的评议，并提出研究人员可以接受、修改或拒绝的修订建议。LitPivot 旨在用于研究构思的早期阶段，但这一思路也可能拓展到篇幅更长的写作任务（例如撰写论文的引言部分）。With collaborators at the University of Pennsylvania, we developed LitPivot, a system that helps researchers navigate these pivots. Using papers retrieved through Asta Paper Finder, LitPivot organizes literature around the part of a proposal being edited, offers critiques supported by excerpts from selected studies, and suggests revisions that researchers can accept, edit, or reject. LitPivot is intended to be used for early-stage research ideation, but the idea could possibly extend to longer writing tasks (i.e., writing the introduction section of a paper).

在一项涉及 17 名研究人员的研究中，领域专家认为，与使用文本编辑器和 AI 聊天工具提出的研究想法相比，借助 LitPivot 提出的研究想法有更扎实的文献依据。参与者还认为，修改后的研究想法更具新颖性和实用性，并表示自己对相关领域文献的理解更加深入。In a study with 17 researchers, domain experts rated research ideas developed with LitPivot as better grounded in the literature than those developed with a text editor and an AI chat tool. Participants also perceived their revised research ideas as more novel and useful, and reported a stronger understanding of the surrounding literature.

LitPivot 将在底特律举行的 UIST 2026 上亮相。点击此处阅读论文。LitPivot will be presented at UIST 2026 in Detroit. Read the paper here.

为什么转型很难 Why pivoting is hard

研究思路在与文献的交流中不断演变。通过分析四个已完成计算机科学研究项目的会议记录，我们在这四个项目中共识别出 21 次由文献引发的方向转变。这些转变分为两类：一是将某个想法与已有研究区分开来，以确立其新颖性；二是使某个想法与已有研究相契合，以便在此基础上继续推进。本项目本身也经历了两次方向转变，之后才确定了研究贡献。Research ideas evolve through engaging with the literature. In our analysis of meeting notes from four completed computer science research projects, we identified 21 literature-initiated pivots across all four projects. These fell into two types: differentiating an idea from existing work to establish an idea’s novelty, and aligning an idea with existing work to build on it. This project itself went through two pivots before we settled on its contributions.

这些变化可能难以应对。在一项形成性研究中，五位研究人员使用文本编辑器和常规搜索工具提出方案。他们发现，一边构思，一边依据文献对想法进行批判性评估并不容易。当某篇论文质疑某个想法的新颖性时，他们希望获得有文献依据的具体修改建议。这些发现影响了 LitPivot 的评估方式：它将有文献支持的批评与针对想法中所选部分的具体修改建议结合起来。These changes can be difficult to navigate. In a formative study, five researchers developed proposals using a text editor and standard search tools. They struggled to develop their ideas while critically evaluating them against the literature. When a paper challenged an idea’s novelty, they wanted concrete suggestions for how to revise it, supported by prior work. These findings shaped LitPivot’s assessments, which pair literature-supported critiques with specific suggestions for revising the selected part of an idea.

LitPivot 的工作原理 How LitPivot works

在 LitPivot 中，研究者首先在编辑器中撰写一份简短的提案，并启用我们称为“分面高亮”的功能。该功能会将一项明确表述的想法划分为不同分面（即问题、贡献和评估）。为了检查某个提案分面，研究者点击草稿中的相应片段。相邻面板会根据所选分面对相关论文进行分组（例如，选中评估分面时，按论文采用的评估方法分组），并突出显示最相关的论文组。研究者选择论文、请求评估，并查看建议的修改内容以及支持该批评意见的摘录。随后，系统会根据相关性对文献重新排序，以匹配修改后的分面。In LitPivot, a researcher starts by writing a short proposal in an editor and enabling what we call facet highlighting, which segments an articulated idea into different facets (i.e., a problem, contribution, and evaluation). To check a proposed facet, the researcher clicks that segment in the draft. An adjacent panel groups related papers based on the selected facet (e.g., grouping papers by the evaluation methods they use when the evaluation facet is selected) and highlights the most relevant groups. The researcher selects papers, requests an assessment, and reviews a suggested revision alongside excerpts supporting the critique. The literature is then reranked based on relevance to the revised facet.

具体而言，LitPivot 将一个研究构想拆分为问题、拟议贡献和评估计划。每个方面都有各自的相关文献集合及其相关性排序。LitPivot 会围绕正在编辑的方面对检索到的论文进行分组，让研究者选择系统应使用哪些论文来评估草稿。In particular, LitPivot separates a research idea into its problem, proposed contribution, and evaluation plan. Each facet has its own set and relevance ranking of related literature. LitPivot groups retrieved papers around the facet being edited, letting the researcher choose which ones the system should use to assess the draft.

与 Prism 等科学写作环境和 Claude Code 等智能体助手并行，LitPivot 探索了一种开发早期研究构想的新工作流程：选择文献来评估构想，利用这些证据对其进行修改，并随着构想的变化重新审视哪些论文具有重要意义。它通过论文分组和关联的批评意见，让提案的每个部分都清晰呈现这些步骤，同时由研究人员掌控草稿以及用于评估草稿的证据。Alongside scientific-writing environments such as Prism and agentic assistants such as Claude Code, LitPivot explores a new workflow for developing an early research idea: choosing literature to assess it against, using that evidence to revise it, and reconsidering which papers matter as the idea changes. Its paper groups and linked critiques make those steps explicit for each part of the proposal, while researchers control both the draft and the evidence used to assess it.

对于问题陈述，LitPivot 会寻找证据，确认该问题确实存在，并说明其重要性。对于拟议的研究贡献，它会将所选论文已经解决的问题与论文指出的局限和未来工作进行比较，以寻找尚未填补的空白。对于评估计划，它会检查拟议的测试是否回应了研究问题，以及类似研究是如何进行评估的。随后，系统会给出修改建议，并附上支持性引文。For a problem statement, LitPivot looks for evidence that the problem exists and reasons it matters. To assess a proposed contribution, it compares what the selected papers have already addressed with the limitations and future work they describe, looking for remaining gaps. For an evaluation plan, it checks whether the proposed tests address the research question and how similar work has been evaluated. The system then suggests a rewrite with supporting quotes attached.

改变想法的某个方面，可能会导致其他方面过时。LitPivot 会标记可能需要修订的段落，例如评估计划已无法充分评估修改后的贡献。研究人员可以接受、编辑或拒绝建议，也可以随着提案的完善请求新的论文，或刷新文献排名。Changing one facet of an idea can leave another out of date. LitPivot flags passages that may need revision, such as an evaluation plan that no longer adequately evaluates a revised contribution. Researchers can accept, edit, or reject suggestions, and request new papers or refresh the literature ranking as their proposal develops.

对一位研究参与者所举示例的转述。Paraphrased example from one study participant.

我们的研究结果 Our findings

在我们的实验室研究中，17 位研究人员各自使用 LitPivot 开发一项指定的想法，并使用基线工具开发另一项——该工具由文本编辑器和一款用于询问所选论文的 AI 工具组成。两种条件使用了相同的论文集。两位领域专家并不知道使用的是哪种系统，他们依据单一标准对最终方案进行评分：方案在多大程度上利用相关文献来支持和论证想法。使用 LitPivot 开发的方案获得了更高的评分。In our lab study, 17 researchers each developed one assigned idea with LitPivot and another with a baseline tool—a text editor and an AI tool for asking questions about selected papers. Both conditions used the same collection of papers. Two domain experts, unaware of which system had been used, rated the resulting proposals on a single criterion: how well they used relevant literature to support and justify the idea. Proposals developed with LitPivot received higher ratings.

同一项研究中的参与者还报告称，与基线方法相比，使用 LitPivot 能让他们更深入地理解相关文献，并且他们自评想法的新颖性和实用性提升幅度更大。领域专家也评审了参与者的想法，并认为经 LitPivot 修改后的想法显著更有相关文献依据。Participants in the same study also reported a stronger understanding of the surrounding literature and greater self-reported improvements in their ideas’ novelty and usefulness with LitPivot than with the baseline. Domain experts also reviewed the participants’ ideas and rated the ideas revised using LitPivot to be significantly better grounded in relevant literature.

我们实验室研究中的一位参与者最初提出，生成一致且符合事实的合成医疗记录。LitPivot 指出，所选文献中可能存在一个研究空白：如何确保多次住院就诊记录之间的一致性。参与者查看了论文摘要，并剔除了有关单次就诊记录的论文。经过再次评估后，他们将提案范围缩小为检测多次就诊记录之间的矛盾。这个例子展示了，修改想法与选择用于评估该想法的文献可以相互启发。One participant in our lab study started with a proposal to generate consistent, factual synthetic medical notes. LitPivot identified consistency across multiple hospital visits as a potential gap in the selected literature. The participant reviewed abstracts and removed papers about single-visit notes. After another assessment, they narrowed the proposal to detecting contradictions across notes from multiple visits. The example shows how revising an idea and choosing the literature used to assess it can inform each other.

在一项后续研究中，五位研究人员在各自正在进行的项目中使用 LitPivot，每次使用时长为 30 分钟。参与者在项目的多个阶段都使用了 LitPivot，而不只是项目初期。两人用它对照文献评估新想法，另外三人则用它来完善更成熟想法的框架。一位研究人员特别指出，看到来自不同领域的相似概念，有助于他们重新界定自己的贡献。In a follow-up study, five researchers used LitPivot on their own ongoing projects during 30-minute sessions. Participants used LitPivot across multiple project phases, not just at the beginning. Two used it to vet new ideas against the literature, while three used it to refine the framing of more mature ideas. One researcher highlighted how seeing parallel concepts from different domains helped them reframe their contribution.

这些研究表明，LitPivot 既能支持早期探索，也能帮助完善现有的研究方向。These studies suggest that LitPivot can support both early exploration and the refinement of an existing research direction.

支持科学发现 Supporting scientific discovery

在 Ai2，我们正在开发 AI，帮助研究人员提出可检验的想法，并考察这些想法背后的证据。Asta 通过基于已发表研究结果生成理论（Theorizer）、综合研究成果，以及基于数据生成和检验假设（AutoDiscovery），为这项工作提供支持；HARPA 则结合新兴研究趋势，生成有前景的假设。Scideator 让研究人员能够重新组合以往研究的要素，提出新想法并评估其新颖性；IdeaSynth 则支持研究人员在以文献为依据的反馈中不断迭代完善想法。At Ai2, we’re developing AI to help researchers formulate testable ideas and examine the evidence behind them. Asta supports that effort through theory generation from published findings (Theorizer), synthesis, and hypothesis generation and testing on data (AutoDiscovery), while HARPA generates promising hypotheses informed by emerging research trends. Scideator lets researchers recombine elements of prior work into new ideas and assess their novelty, and IdeaSynth supports iterative refinement with feedback grounded in the literature.

我们近期的研究《旧观点，新问题》探讨了自动化新颖性评估的局限，展示了提示词的细微改动如何改变 AI 评审器对同一想法的判定。LitPivot 延续了这项研究，将相关文献的选择纳入修改过程。随着想法逐步发展，研究人员可以更换用于评估提案的论文，再根据评议和支持性摘录决定如何修改提案。该系统将这些决策与提案的问题、贡献和评估计划关联起来。Our recent study, Old Ideas, Novel Problems, examines the limits of automated novelty evaluation, showing how small prompt changes can alter an AI judge’s verdict on the same ideas. LitPivot extends this line of work by making the choice of relevant literature part of the revision process. Researchers can change which papers they use to assess a proposal as their idea develops, then use critiques and supporting excerpts to decide how to revise it. The system connects those decisions across the proposal’s problem, contribution, and evaluation plan.

我们希望 LitPivot 带来的见解能帮助科学家在现有知识的基础上进一步探索，并将早期构想转化为各自领域的新贡献。We hope insights from LitPivot help scientists build on existing knowledge and turn early ideas into new contributions to their fields.