Author name cluster

Mohammad Raza

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

IJCAI Conference 2025 Conference Paper

Instantiation-based Formalization of Logical Reasoning Tasks Using Language Models and Logical Solvers

Mohammad Raza
Natasa Milic-Frayling

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.

PDF Details DOI

AAAI Conference 2018 Conference Paper

Disjunctive Program Synthesis: A Robust Approach to Programming by Example

Mohammad Raza
Sumit Gulwani

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 possible 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.

PDF Details

AAAI Conference 2017 Conference Paper

Automated Data Extraction Using Predictive Program Synthesis

Mohammad Raza
Sumit Gulwani

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 inputoutput 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.

PDF Details

IJCAI Conference 2015 Conference Paper

Compositional Program Synthesis from Natural Language and Examples

Mohammad Raza
Sumit Gulwani
Natasa Milic-Frayling

Compositionality is a fundamental notion in computation whereby complex abstractions can be constructed from simpler ones, yet this property has so far escaped the paradigm of end-user programming from examples or natural language. Existing approaches restrict end users to only give holistic specifications of tasks, which limits the expressivity and scalability of these approaches to relatively simple programs in very restricted domains. In this paper we propose Compositional Program Synthesis (CPS): an approach in which tasks can be specified in a compositional manner through a combination of natural language and examples. We present a domain-agnostic program synthesis algorithm and demonstrate its application to an expressive string manipulation language. We evaluate our approach on complex tasks from online help forums that are beyond the scope of current state-ofthe-art methods.

PDF Details

AAAI Conference 2014 Conference Paper

Programming by Example Using Least General Generalizations

Mohammad Raza
Sumit Gulwani
Natasa Milic-Frayling

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 stateof-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.

PDF Details