Robustness of reasoning remains a significant challenge for large language models, and addressing it is essential for the practical applicability of AI-driven reasoning systems. We introduce Semantic Self-Verification (SSV), a novel approach that addresses the key challenge in combining language models with the rigor of logical solvers: to accurately formulate the reasoning problem from natural language to the formal language of the solver. SSV uses a consistency-based approach to produce strong abstract formalizations of problems using concrete instantiations that are generated by the model and verified by the solver. In addition to significantly advancing the overall reasoning accuracy over the state-of-the-art, a key novelty that this approach presents is a feature of verification that has near-perfect precision over a significant coverage of cases, as we demonstrate on open reasoning benchmarks. We propose such *near-certain reasoning* as a new approach to reduce the need for manual verification in many cases, taking us closer to more dependable and autonomous AI reasoning systems.

Formatting is an important property in tables for visualization, presentation, and analysis. Spreadsheet software allows users to automatically format their tables by writing data-dependent conditional formatting (CF) rules. Writing such rules is often challenging for users as it requires understanding and implementing the underlying logic. We present FormaT5, a transformer-based model that can generate a CF rule given the target table and a natural language description of the desired formatting logic. We find that user descriptions for these tasks are often under-specified or ambiguous, making it harder for code generation systems to accurately learn the desired rule in a single step. To tackle this problem of under-specification and minimise argument errors, FormaT5 learns to predict placeholders though an abstention objective. These placeholders can then be filled by a second model or, when examples of rows that should be formatted are available, by a programming-by-example system. To evaluate FormaT5 on diverse and real scenarios, we create an extensive benchmark of 1053 CF tasks, containing real-world descriptions collected from four different sources. We release our benchmarks to encourage research in this area. Abstention and filling allow FormaT5 to outperform 8 different neural approaches on our benchmarks, both with and without examples. Our results illustrate the value of building domain-specific learning systems.

Spreadsheets are widely used for table manipulation and presentation. Stylistic formatting of these tables is an important property for presentation and analysis. As a result, popular spreadsheet software, such as Excel, supports automatically formatting tables based on rules. Unfortunately, writing such formatting rules can be challenging for users as it requires knowledge of the underlying rule language and data logic. We present Cornet, a system that tackles the novel problem of automatically learning such formatting rules from user-provided formatted cells. Cornet takes inspiration from advances in inductive programming and combines symbolic rule enumeration with a neural ranker to learn conditional formatting rules. To motivate and evaluate our approach, we extracted tables with over 450K unique formatting rules from a corpus of over 1.8M real worksheets. Since we are the first to introduce the task of automatically learning conditional formatting rules, we compare Cornet to a wide range of symbolic and neural baselines adapted from related domains. Our results show that Cornet accurately learns rules across varying setups. Additionally, we show that in some cases Cornet can find rules that are shorter than those written by users and can also discover rules in spreadsheets that users have manually formatted. Furthermore, we present two case studies investigating the generality of our approach by extending Cornet to related data tasks (e.g., filtering) and generalizing to conditional formatting over multiple columns.

We propose a new approach to extracting data items or field values from semi-structured documents. Examples of such problems include extracting passenger name, departure time and departure airport from a travel itinerary, or extracting price of an item from a purchase receipt. Traditional approaches to data extraction use machine learning or program synthesis to process the whole document to extract the desired fields. Such approaches are not robust to for- mat changes in the document, and the extraction process typically fails even if changes are made to parts of the document that are unrelated to the desired fields of interest. We propose a new approach to data extraction based on the concepts of landmarks and regions. Humans routinely use landmarks in manual processing of documents to zoom in and focus their attention on small regions of interest in the document. Inspired by this human intuition, we use the notion of landmarks in program synthesis to automatically synthesize extraction programs that first extract a small region of interest, and then automatically extract the desired value from the region in a subsequent step. We have implemented our landmark based extraction approach in a tool LRSyn, and show extensive valuation on documents in HTML as well as scanned images of invoices and receipts. Our results show that the our approach is robust to various types of format changes that routinely happen in real-world settings

Integrated Development Environments (IDEs) provide tool support to automate many source code editing tasks. Traditionally, IDEs use only the spatial context, i.e., the location where the developer is editing, to generate candidate edit recommendations. However, spatial context alone is often not sufficient to confidently predict the developer’s next edit, and thus IDEs generate many suggestions at a location. Therefore, IDEs generally do not actively offer suggestions and instead, the developer is usually required to click on a specific icon or menu and then select from a large list of potential suggestions. As a consequence, developers often miss the opportunity to use the tool support because they are not aware it exists or forget to use it. To better understand common patterns in developer behavior and produce better edit recommendations, we can additionally use the temporal context, i.e., the edits that a developer was recently performing. To enable edit recommendations based on temporal context, we present Overwatch, a novel technique for learning edit sequence patterns from traces of developers’ edits performed in an IDE. Our experiments show that Overwatch has 78% precision and that Overwatch not only completed edits when developers missed the opportunity to use the IDE tool support but also predicted new edits that have no tool support in the IDE.

Multi-modal program synthesis refers to the task of synthesizing programs (code) from their specification given in different forms, such as a combination of natural language and examples. Examples provide a precise but incomplete specification, and natural language provides an ambiguous but more "complete" task description. Machine-learned pre-trained models (PTMs) are adept at handling ambiguous natural language, but struggle with generating syntactically and semantically precise code. Program synthesis techniques can generate correct code, often even from incomplete but precise specifications, such as examples, but they are unable to work with the ambiguity of natural languages. We present an approach that combines PTMs with component-based synthesis (CBS): PTMs are used to generate candidates programs from the natural language description of the task, which are then used to guide the CBS procedure to find the program that matches the precise examples-based specification. We use our combination approach to instantiate multi-modal synthesis systems for two programming domains: the domain of regular expressions and the domain of CSS selectors. Our evaluation demonstrates the effectiveness of our domain-agnostic approach in comparison to a state-of-the-art specialized system, and the generality of our approach in providing multi-modal program synthesis from natural language and examples in different programming domains.

Automatic synthesis of web data extraction programs has been explored in a variety of settings, but in practice there remain various robustness and usability challenges. In this work we present a novel program synthesis approach which combines the benefits of deductive and enumerative synthesis strategies, yielding a semi-supervised technique with which concise programs expressible in standard languages can be synthesized from very few examples. We demonstrate improvement over existing techniques in terms of overall accuracy, number of examples required, and program complexity. Our method has been deployed as a web extraction feature in the mass market Microsoft Power BI product.

Data repositories often consist of text files in a wide variety of standard formats, ad-hoc formats, as well as mixtures of formats where data in one format is embedded into a different format. It is therefore a significant challenge to parse these files into a structured tabular form, which is important to enable any downstream data processing. We present Unravel, an extensible framework for structure interpretation of ad-hoc formats. Unravel can automatically, with no user input, extract tabular data from a diverse range of standard, ad-hoc and mixed format files. The framework is also easily extensible to add support for previously unseen formats, and also supports interactivity from the user in terms of examples to guide the system when specialized data extraction is desired. Our key insight is to allow arbitrary combination of extraction and parsing techniques through a concept called partial structures . Partial structures act as a common language through which the file structure can be shared and refined by different techniques. This makes Unravel more powerful than applying the individual techniques in parallel or sequentially. Further, with this rule-based extensible approach, we introduce the novel notion of re-interpretation where the variety of techniques supported by our system can be exploited to improve accuracy while optimizing for particular quality measures or restricted environments. On our benchmark of 617 text files gathered from a variety of sources, Unravel is able to extract the intended table in many more cases compared to state-of-the-art techniques.

Programming by example (PBE) systems allow end users to easily create programs by providing a few input-output examples to specify their intended task. The system attempts to generate a program in a domain specific language (DSL) that satisfies the given examples. However, a key challenge faced by existing PBE techniques is to ensure the robustness of the programs that are synthesized from a small number of examples, as these programs often fail when applied to new inputs. This is because there can be many possible programs satisfying a small number of examples, and the PBE system has to somehow rank between these candidates and choose the correct one without any further information from the user. In this work we present a different approach to PBE in which the system avoids making a ranking decision at the synthesis stage, by instead synthesizing a disjunctive program that includes the many top-ranked programs as possible alternatives and selects between these different choices upon execution on a new input. This delayed choice brings the important benefit of comparing the possible outputs produced by the different disjuncts on a given input at execution time. We present a generic framework for synthesizing such disjunctive programs in arbitrary DSLs, and describe two concrete implementations of disjunctive synthesis in the practical domains of data extraction from plain text and HTML documents. We present an evaluation showing the significant increase in robustness achieved with our disjunctive approach, as illustrated by an increase from 59% to 93% of tasks for which correct programs can be learnt from a single example.

In recent years there has been rising interest in the use of programming-by-example techniques to assist users in data manipulation tasks. Such techniques rely on an explicit input-output examples specification from the user to automatically synthesize programs. However, in a wide range of data extraction tasks it is easy for a human observer to predict the desired extraction by just observing the input data itself. Such predictive intelligence has not yet been explored in program synthesis research, and is what we address in this work. We describe a predictive program synthesis algorithm that infers programs in a general form of extraction DSLs (domain specific languages) given input-only examples. We describe concrete instantiations of such DSLs and the synthesis algorithm in the two practical application domains of text extraction and web extraction, and present an evaluation of our technique on a range of extraction tasks encountered in practice.

Good alignment and repetition of objects across presentation slides can facilitate visual processing and contribute to audience understanding. However, creating and maintaining such consistency during slide design is difficult. To solve this problem, we present two complementary tools: (1) StyleSnap, which increases the alignment and repetition of objects by adaptively clustering object edge positions and allowing parallel editing of all objects snapped to the same spatial extent; and (2) FlashFormat, which infers the least-general generalization of editing examples and applies it throughout the selected range. In user studies of repetitive styling task performance, StyleSnap and FlashFormat were 4-5 times and 2-3 times faster respectively than conventional editing. Both use a mixed-initiative approach to improve the consistency of slide decks and generalize to any situations involving direct editing across disjoint visual spaces.

Recent advances in Programming by Example (PBE) have supported new applications to text editing, but existing approaches are limited to simple text strings. In this paper we address transformations in richly formatted documents, using an approach based on the idea of least general generalizations from inductive inference, which avoids the scalability issues faced by state-of-the-art PBE methods. We describe a novel domain specific language (DSL) that expresses transformations over XML structures describing richly formatted content, and a synthesis algorithm that generates a minimal program with respect to a natural subsumption ordering in our DSL. We present experimental results on tasks collected from online help forums, showing an average of 4.17 examples required for task completion.

An important aspect in understanding and classifying protein-protein interactions (PPI) is to analyze their interfaces in order to distinguish between transient and obligate complexes. We propose a classification approach to discriminate between these two types of complexes. Our approach has two important aspects. First, we have used desolvation energies - amino acid and atom type - of the residues present in the interface, which are the input features of the classifiers. Principal components of the data were found and then the classification is performed via linear dimensionality reduction (LDR) methods. Second, we have investigated various interface properties of these interactions. From the analysis of protein quaternary structures, physicochemical properties are treated as the input features of the classifiers. Various features are extracted from each complex, and the classification is performed via different linear dimensionality reduction (LDR) methods. The results on standard benchmarks of transient and obligate protein complexes show that (i) desolvation energies are better discriminants than solvent accessibility and conservation properties, among others, and (ii) the proposed approach outperforms previous solvent accessible area based approaches using support vector machines.