Publications

2024

1. EMNLP 2024

   Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning

   Shramay Palta, Nishant Balepur, Peter A. Rankel, Sarah Wiegreffe, Marine Carpuat, and Rachel Rudinger

   Findings of the Association for Computational Linguistics: EMNLP 2024

   Abstract Bib PDF Poster Data Video

   Questions involving commonsense reasoning about everyday situations often admit many possible or plausible answers. In contrast, multiple-choice question (MCQ) benchmarks for commonsense reasoning require a hard selection of a single correct answer, which, in principle, should represent the most plausible answer choice. On 250 MCQ items sampled from two commonsense reasoning benchmarks, we collect 5,000 independent plausibility judgments on answer choices. We find that for over 20% of the sampled MCQs, the answer choice rated most plausible does not match the benchmark gold answers; upon manual inspection, we confirm that this subset exhibits higher rates of problems like ambiguity or semantic mismatch between question and answer choices. Experiments with LLMs reveal low accuracy and high variation in performance on the subset, suggesting our plausibility criterion may be helpful in identifying more reliable benchmark items for commonsense evaluation.

   @inproceedings{palta-etal-2024-plausibly,
     abbr = EMNLP,
     title = "Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning",
     author = "Palta, Shramay and Balepur, Nishant  and Rankel, Peter A. and Wiegreffe, Sarah  and Carpuat, Marine and Rudinger, Rachel",
     booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
     month = nov,
     year = "2024",
     publisher = "Association for Computational Linguistics",
     address = "Miami, Florida, USA",
     url = "https://aclanthology.org/2024.findings-emnlp.198",
     pages = "3451--3473",
     abstract = "Questions involving commonsense reasoning about everyday situations often admit many possible or plausible answers. In contrast, multiple-choice question (MCQ) benchmarks for commonsense reasoning require a hard selection of a single correct answer, which, in principle, should represent the most plausible answer choice. On 250 MCQ items sampled from two commonsense reasoning benchmarks, we collect 5,000 independent plausibility judgments on answer choices. We find that for over 20% of the sampled MCQs, the answer choice rated most plausible does not match the benchmark gold answers; upon manual inspection, we confirm that this subset exhibits higher rates of problems like ambiguity or semantic mismatch between question and answer choices. Experiments with LLMs reveal low accuracy and high variation in performance on the subset, suggesting our plausibility criterion may be helpful in identifying more reliable benchmark items for commonsense evaluation."
   }

1. ECCV 2024

   Measuring Style Similarity in Diffusion Models

   Gowthami Somepalli, Anubhav Gupta, Kamal Gupta, Shramay Palta, Micah Goldblum, Jonas Geiping, Abhinav Shrivastava, and Tom Goldstein

   The 18th European Conference on Computer Vision: ECCV 2024

   Abstract Bib PDF Code

   Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication in text-to-image models. We present a framework for understanding and extracting style descriptors from images. Our framework comprises a new dataset curated using the insight that style is a subjective property of an image that captures complex yet meaningful interactions of factors including but not limited to colors, textures, shapes, etc. We also propose a method to extract style descriptors that can be used to attribute style of a generated image to the images used in the training dataset of a text-to-image model. We showcase promising results in various style retrieval tasks. We also quantitatively and qualitatively analyze style attribution and matching in the Stable Diffusion model. Code and artifacts are available at this https URL.

   @article{somepalli2024measuring,
     title = Measuring Style Similarity in Diffusion Models,
     author = "Gowthami Somepalli and Anubhav Gupta and Kamal Gupta and Shramay Palta and Micah Goldblum and Jonas Geiping and Abhinav Shrivastava and Tom Goldstein",
     journal = {arXiv preprint arXiv:2404.01292},
     year = "2024"
   }

1. ACL 2024

   It’s Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning

   Nishant Balepur, Shramay Palta, and Rachel Rudinger

   Findings of the Association for Computational Linguistics: ACL 2024

   Abstract Bib PDF

   Chain-of-thought (COT) prompting can help large language models (LLMs) reason toward correct answers, but its efficacy in reasoning toward incorrect answers is unexplored. This strategy of process of elimination (PoE), when used with COT, has the potential to enhance interpretability in tasks like medical diagnoses of exclusion. Thus, we propose PoE with COT, a new task where LLMs must reason toward incorrect options on multiple-choice questions. We evaluate the ability of GPT-3.5, LLaMA-2, and Falcon to perform PoE with COT on 2-choice commonsense and scientific reasoning datasets. We show that PoE consistently underperforms directly choosing the correct answer. The agreement of these strategies is also lower than the self-consistency of each strategy. To study these issues further, we conduct an error analysis and give suggestions for future work.

   @inproceedings{balepur-etal-2024-easy,
       abbr = ACL,
       title = "It's Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning",
       author = "Balepur, Nishant and Palta, Shramay  and Rudinger, Rachel",
       booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
       month = aug,
       year = "2024",
       publisher = "Association for Computational Linguistics",
       address = "Bangkok, Thailand and virtual meeting",
       url = "https://aclanthology.org/2024.findings-acl.604",
       pages = "10143--10166",
       abstract = "Chain-of-thought (COT) prompting can help large language models (LLMs) reason toward correct answers, but its efficacy in reasoning toward incorrect answers is unexplored. This process of elimination (PoE), when used with COT, can enhance self-consistency, interpretability, and tasks such as medical diagnoses of exclusion. Thus, we propose PoE with COT, where LLMs must reason toward incorrect options on multiple-choice questions. We evaluate the ability of GPT-3.5, LLaMA-2, and Falcon to perform PoE with COT on a total of four commonsense and scientific reasoning datasets. We find that the strategy of PoE always underperforms the strategy of choosing the correct answer. The agreement of these strategies is also lower than the self-consistency of each strategy. To study these issues further, we conduct error analyses and give suggestions for future work"
   }

2023

1. ACL 2023

   FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models

   Shramay Palta, and Rachel Rudinger

   Findings of the Association for Computational Linguistics: ACL 2023

   Abstract Bib PDF Poster Dataset Video

   It is common sense that one should prefer to eat a salad with a fork rather than with a chainsaw. However, for eating a bowl of rice, the choice between a fork and a pair of chopsticks is culturally relative. We introduce FORK, a small, manually-curated set of CommonsenseQA-style questions for probing cultural biases and assumptions present in com- monsense reasoning systems, with a specific focus on food-related customs. We test several CommonsenseQA systems on FORK, and while we see high performance on questions about the US culture, the poor performance of these systems on questions about non-US cultures highlights systematic cultural biases aligned with US over non-US cultures.

   @inproceedings{palta-rudinger-2023-fork,
     abbr = ACL,
     title = "{FORK}: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models",
     author = "Palta, Shramay  and Rudinger, Rachel",
     booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
     month = jul,
     year = "2023",
     publisher = "Association for Computational Linguistics",
     address = "Toronto, Canada",
     url = "https://aclanthology.org/2023.findings-acl.631",
     pages = "9952--9962",
     abstract = "It is common sense that one should prefer to eat a salad with a fork rather than with a chainsaw. However, for eating a bowl of rice, the choice between a fork and a pair of chopsticks is culturally relative. We introduce FORK, a small, manually-curated set of CommonsenseQA-style questions for probing cultural biases and assumptions present in commonsense reasoning systems, with a specific focus on food-related customs. We test several CommonsenseQA systems on FORK, and while we see high performance on questions about the US culture, the poor performance of these systems on questions about non-US cultures highlights systematic cultural assumptions aligned with US over non-US cultures."
   }

2022

1. arXiv

   Investigating Information Inconsistency in Multilingual Open-Domain Question Answering

   Shramay Palta, Haozhe An, Yifan Yang, Shuaiyi Huang, and Maharshi Gor

   arXiv preprint, 2022

   Abstract Bib PDF

   Multilingual open-domain question answering can unlock information that might be unavailable in a user's primary language. However, can that user trust the information they get? But multilingual question answering can potentially expose users to unreliable information through cultural differences, divergent national laws, or uneven resources. To understand the effects of the biased availability of information and cultural influence, we analyze the behavior of multilingual open-domain question answering models with a focus on retrieval bias. We analyze if different retriever models present different passages---and answers---given the same question in different languages on TyDi QA and XOR-TyDi QA, two multilingual QA datasets. While most answers are consistent, where they differ reveals valuable information about per-language resources disparity, and linguistic variation.

   @article{palta2022investigating,
     title = {Investigating Information Inconsistency in Multilingual Open-Domain Question Answering},
     author = {Palta, Shramay and An, Haozhe and Yang, Yifan and Huang, Shuaiyi and Gor, Maharshi},
     journal = {arXiv preprint arXiv:2205.12456},
     year = {2022}
   }