most citedEvaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis

1 citations · 1 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CL2025

Towards Semantic Integration of Opinions: Unified Opinion Concepts Ontology and Extraction Task

Gaurav Negi, Dhairya Dalal, Omnia Zayed +1

This paper introduces the Unified Opinion Concepts (UOC) ontology to integrate opinions within their semantic context. The UOC ontology bridges the gap between the semantic represe…

cs.AI2025

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering

Marco Valentino, Geonhee Kim, Dhairya Dalal +2

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, wh…

cs.AI2025

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement

Xin Quan, Marco Valentino, Danilo S. Carvalho +2

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the…

cs.IR2025

A Semantic Search Pipeline for Causality-driven Adhoc Information Retrieval

Dhairya Dalal, Sharmi Dev Gupta, Bentolhoda Binaei

We present a unsupervised semantic search pipeline for the Causality-driven Adhoc Information Retrieval (CAIR-2021) shared task. The CAIR shared task expands traditional informatio…

cs.LG20201 cited

Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis

Dhairya Dalal, Byron V. Galbraith

Implementing enterprise process automation often requires significant technical expertise and engineering effort. It would be beneficial for non-technical users to be able to descr…