Papers by Soumya Sanyal

8 papers
RobustLR: A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models that perform deductive reasoning on inputs containing rules and statements in the English natural language do not perform consistently on the RobustLR test set.
Approach: They propose a diagnostic benchmark that evaluates the robustness of language models to minimal logical edits in inputs and different logical equivalence conditions.
Outcome: The proposed models do not perform consistently on the RobustLR test set.
Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification (2024.findings-acl)

Copied to clipboard

Challenge: Existing evidence that humans make numerous inferences to understand discourse and text is not fully understood.
Approach: They propose to use textual inference datasets with multi-sentence premises to solve the entailment verification problem.
Outcome: The proposed model outperforms GPT-3.5 and rivals GPL-4 in EV tasks.
FaiRR: Faithful and Robust Deductive Reasoning over Natural Language (2022.acl-long)

Copied to clipboard

Challenge: Currently, black-box models generate both the proof graph and intermediate inferences within the same model and thus may be unfaithful.
Approach: They propose a transformer-based model that can perform deductive reasoning on a logical rulebase containing rules and statements written in natural language.
Outcome: The proposed model is robust to language perturbations and faster at inference than previous models on existing reasoning datasets.
Self-contradictory reasoning evaluation and detection (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have shown impressive reasoning ability, but many downstream reasoning tasks focus on performance-wise evaluation.
Approach: They define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-contra reasoning.
Outcome: The proposed model can detect self-contra reasoning with a 52.2% F1 score, much lower than for humans.
Discretized Integrated Gradients for Explaining Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation.
Approach: They propose an attribution-based explanation algorithm that uses averaging the model's output gradient interpolated along a straight-line path in the input data space.
Outcome: The proposed method is compared with IG on multiple sentiment classification datasets.
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to improve logical reasoning skills require complex data processing.
Approach: They propose an adaptive pretraining approach to improve logical reasoning over text . they use a subset of Wikipedia sentences for pretraining and a sentence-level classification loss .
Outcome: The proposed model outperforms baselines on LogiQA and ReClor.
A Re-evaluation of Knowledge Graph Completion Methods (2020.acl-main)

Copied to clipboard

Challenge: Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Approach: They propose a protocol to evaluate KGC methods that is robust to handle bias in the model, which can substantially affect the final results.
Outcome: The proposed evaluation protocol is robust to handle bias in the model, which can substantially affect the final results.
Mixing Inference-time Experts for Enhancing LLM Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for improving reasoning quality in large language models are limited to using a single expert.
Approach: They propose a framework that finetunes and merges expert logits from one LLM . they use commonsense and entailment reasoning experts to improve chain-of-thought reasoning .
Outcome: The proposed framework outperforms baselines on three question-answering datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations