Naman Bansal

Yash Mahajan, Naman Bansal, Shubhra Kanti Karmaker

In this paper, we adopted a retrospective approach to examine and compare five existing popular sentence encoders, i.e., Sentence-BERT, Universal Sentence Encoder (USE), LASER, InferSent, and Doc2vec, in terms of their performance on downstream tasks versus their capability to capture basic semantic properties. Initially, we evaluated all five sentence encoders on the popular SentEval benchmark and found that multiple sentence encoders perform quite well on a variety of popular downstream tasks. However, being unable to find a single winner in all cases, we designed further experiments to gain a deeper understanding of their behavior. Specifically, we proposed four semantic evaluation criteria, i.e., Paraphrasing, Synonym Replacement, Antonym Replacement, and Sentence Jumbling, and evaluated the same five sentence encoders using these criteria. We found that the Sentence-Bert and USE models pass the paraphrasing criterion, with SBERT being the superior between the two. LASER dominates in the case of the synonym replacement criterion. Interestingly, all the sentence encoders failed the antonym replacement and jumbling criteria. These results suggest that although these popular sentence encoders perform quite well on the SentEval benchmark, they still struggle to capture some basic semantic properties, thus, posing a daunting dilemma in NLP research.

Yash Mahajan, Matthew Freestone, Naman Bansal et al.

Large Language Models (LLMs) have recently shown remarkable advancement in various NLP tasks. As such, a popular trend has emerged lately where NLP researchers extract word/sentence/document embeddings from these large decoder-only models and use them for various inference tasks with promising results. However, it is still unclear whether the performance improvement of LLM-induced embeddings is merely because of scale or whether underlying embeddings they produce significantly differ from classical encoding models like Word2Vec, GloVe, Sentence-BERT (SBERT) or Universal Sentence Encoder (USE). This is the central question we investigate in the paper by systematically comparing classical decontextualized and contextualized word embeddings with the same for LLM-induced embeddings. Our results show that LLMs cluster semantically related words more tightly and perform better on analogy tasks in decontextualized settings. However, in contextualized settings, classical models like SimCSE often outperform LLMs in sentence-level similarity assessment tasks, highlighting their continued relevance for fine-grained semantics.

Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal et al.

One of the most important yet onerous tasks in the academic peer-reviewing process is composing meta-reviews, which involves assimilating diverse opinions from multiple expert peers, formulating one's self-judgment as a senior expert, and then summarizing all these perspectives into a concise holistic overview to make an overall recommendation. This process is time-consuming and can be compromised by human factors like fatigue, inconsistency, missing tiny details, etc. Given the latest major developments in Large Language Models (LLMs), it is very compelling to rigorously study whether LLMs can help metareviewers perform this important task better. In this paper, we perform a case study with three popular LLMs, i.e., GPT-3.5, LLaMA2, and PaLM2, to assist meta-reviewers in better comprehending multiple experts perspectives by generating a controlled multi-perspective summary (MPS) of their opinions. To achieve this, we prompt three LLMs with different types/levels of prompts based on the recently proposed TELeR taxonomy. Finally, we perform a detailed qualitative study of the MPSs generated by the LLMs and report our findings.

John Salvador, Naman Bansal, Mousumi Akter et al.

Semantic Overlap Summarization (SOS) is a constrained multi-document summarization task, where the constraint is to capture the common/overlapping information between two alternative narratives. In this work, we perform a benchmarking study of popular Large Language Models (LLMs) exclusively on the SOS task. Additionally, we introduce the PrivacyPolicyPairs (3P) dataset to expand the space of SOS benchmarks in terms of quantity and variety. This dataset provides 135 high-quality SOS data samples sourced from privacy policy documents. We then use a standard prompting taxonomy called TELeR to create and evaluate 905,216 distinct LLM-generated summaries over two SOS datasets from different domains, and we further conduct human evaluation on a subset of 540 samples. We conclude the paper by analyzing models' performances and the reliability of automatic evaluation. The code and datasets used to conduct this study are available at https://anonymous.4open.science/r/llm_eval-E16D.

Naman Bansal, Yash mahajan, Sanjeev Sinha et al.

Sentence encoders play a pivotal role in various NLP tasks; hence, an accurate evaluation of their compositional properties is paramount. However, existing evaluation methods predominantly focus on goal task-specific performance. This leaves a significant gap in understanding how well sentence embeddings demonstrate fundamental compositional properties in a task-independent context. Leveraging classical set theory, we address this gap by proposing six criteria based on three core "set-like" compositions/operations: \textit{TextOverlap}, \textit{TextDifference}, and \textit{TextUnion}. We systematically evaluate $7$ classical and $9$ Large Language Model (LLM)-based sentence encoders to assess their alignment with these criteria. Our findings show that SBERT consistently demonstrates set-like compositional properties, surpassing even the latest LLMs. Additionally, we introduce a new dataset of ~$192$K samples designed to facilitate future benchmarking efforts on set-like compositionality of sentence embeddings.

Naman Bansal, Mousumi Akter, Shubhra Kanti Karmaker Santu

In this paper, we introduce an important yet relatively unexplored NLP task called Multi-Narrative Semantic Overlap (MNSO), which entails generating a Semantic Overlap of multiple alternate narratives. As no benchmark dataset is readily available for this task, we created one by crawling 2,925 narrative pairs from the web and then, went through the tedious process of manually creating 411 different ground-truth semantic overlaps by engaging human annotators. As a way to evaluate this novel task, we first conducted a systematic study by borrowing the popular ROUGE metric from text-summarization literature and discovered that ROUGE is not suitable for our task. Subsequently, we conducted further human annotations/validations to create 200 document-level and 1,518 sentence-level ground-truth labels which helped us formulate a new precision-recall style evaluation metric, called SEM-F1 (semantic F1). Experimental results show that the proposed SEM-F1 metric yields higher correlation with human judgement as well as higher inter-rater-agreement compared to ROUGE metric.

Naman Bansal, Chirag Agarwal, Anh Nguyen

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically tuned. High sensitivity to arbitrary hyperparameter choices does not only impede reproducibility but also questions the correctness of an explanation and impairs the trust of end-users. In this paper, we provide a thorough empirical study on the sensitivity of existing attribution methods. We found an alarming trend that many methods are highly sensitive to changes in their common hyperparameters e.g. even changing a random seed can yield a different explanation! Interestingly, such sensitivity is not reflected in the average explanation accuracy scores over the dataset as commonly reported in the literature. In addition, explanations generated for robust classifiers (i.e. which are trained to be invariant to pixel-wise perturbations) are surprisingly more robust than those generated for regular classifiers.