Papers by Adam Poliak
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (D18-1)
Copied to clipboard
Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme
| Challenge: | a plethora of new natural language inference datasets has been created in recent years . however, these datasets do not provide clear insight into what type of reasoning or inference a model may be performing. |
| Approach: | They propose to recast 13 existing natural language inference datasets into a common structure. |
| Outcome: | The proposed datasets provide insight into how well a sentence representation captures distinct types of reasoning. |
Figurative Language in Recognizing Textual Entailment (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing RTE models struggle to capture figurative language, despite its ubiquity, it remains a bottleneck in automatic text understanding. |
| Approach: | They propose to frame five existing figurative language datasets into over 12,500 RTE examples. |
| Outcome: | The proposed models struggle to perform pragmatic inference and reasoning about world knowledge. |
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (N18-2)
Copied to clipboard
| Challenge: | Existing methods to investigate whether sentence representations from NMT systems capture distinct semantic phenomena are limited. |
| Approach: | They propose a process to investigate the extent to which sentence representations arising from neural machine translation systems encode distinct semantic phenomena. |
| Outcome: | The proposed model is suited to supporting inferences at the syntax-semantics interface, compared to anaphora resolution requiring world knowledge. |
Evaluating Paraphrastic Robustness in Textual Entailment Models (2023.acl-short)
Copied to clipboard
| Challenge: | Recognizing Textual Entailment models understand language and should be robust to paraphrases. |
| Approach: | They propose to evaluate whether RTE models are robust to paraphrase . they use 1,126 pairs of Recognizing Textual Entailment (RTE) examples to evaluate their models . |
| Outcome: | The evaluation set shows that models change predictions on 8-16% of paraphrased examples, suggesting that there is room for improvement. |
Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference (2025.coling-main)
Copied to clipboard
| Challenge: | Creating NLP datasets with Large Language Models (LLMs) is an attractive alternative to relying on crowd-source workers. |
| Approach: | They recreate a portion of the Stanford Natural Language Inference corpus using GPT-4, Llama-2 70b for Chat, and Mistral 7b Instruct. |
| Outcome: | The proposed model can be used to generate NLP datasets with stereotypical biases and annotation artifacts. |
Uncertain Natural Language Inference (2020.acl-main)
Copied to clipboard
| Challenge: | Existing categorical bin assignments for NLI are not effective for entailment inference. |
| Approach: | They propose a refinement of Natural Language Inference that targets direct prediction of subjective probability assessments. |
| Outcome: | The proposed model can be used in pre-training and correlates well with humans. |
Temporal Reasoning in Natural Language Inference (2020.findings-emnlp)
Copied to clipboard
| Challenge: | We use five new natural language inference (NLI) datasets focused on temporal reasoning. |
| Approach: | They introduce five new natural language inference datasets focused on temporal reasoning. |
| Outcome: | The proposed models capture the temporal reasoning of four existing datasets. |
Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference (P19-1)
Copied to clipboard
| Challenge: | Natural Language Inference (NLI) datasets often contain hypothesis-only biases . authors propose probabilistic methods to build models that are more robust to such artifacts - a new study shows . |
| Approach: | They propose probabilistic methods to build models that are more robust to biases . authors train on datasets containing biase . |
| Outcome: | The proposed methods can make NLI models more robust to dataset-specific artifacts . the methods transfer better than a baseline architecture in 9 out of 12 NLI datasets compared with baseline architectures based on the proposed methods . |