publications

2026

1. ICML 2026

   Configurable Reward Model for Balanced Safety Alignment

   Zhengping Jiang, Mehran Khodabandeh, Akash Bharadwaj, Manik Bhandari, Mayur Srungarapu, Anqi Liu, Benjamin Van Durme, and Li Chen

   In Forty-third International Conference on Machine Learning, 2026

   Abs HTML PDF

   Aligning large language models (LLMs) to heterogeneous and rapidly evolving safety requirements remains a critical challenge. Existing instruction-tuned LLMs and standalone safety classifiers often fail to generalize to new safety configurations, motivating the need for Reward Models (RMs) that are explicitly configurable to changing specifications. We introduce the Configurable Safety Reward Model (CSRM), which is jointly optimized for calibrated safety compliance and reward modeling. Our approach is supported by configuration-targeted data augmentation that enforces instruction adherence while preserving relative severity structure. The resulting RM is sensitive to fine-grained safety configurations and conversational nuances, substantially improving generalization to previously unseen safety configurations. CSRM achieves state-of-the-art performance on recent configurable safety benchmarks, including CoSApien (94.6% F1) and DynaBench (75.8% F1), without requiring additional human annotation. When used for downstream safety alignment, CSRM yields LLMs with a significantly improved helpfulness-safety tradeoff compared to existing baselines.

2023

1. RecSys 2023

   RecQR: Using Recommendation Systems for Query Reformulation to correct unseen errors in spoken dialog systems

   Manik Bhandari, Mingxian Wang, Oleg Poliannikov, and Kanna Shimizu

   In Proceedings of the 17th ACM Conference on Recommender Systems, 2023

   Abs HTML PDF

   As spoken dialog systems like Siri, Alexa and Google Assistant become widespread, it becomes apparent that relying solely on global, one-size-fits-all models of Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Entity Resolution (ER), is inadequate for delivering a friction-less customer experience. To address this issue, Query Reformulation (QR) has emerged as a crucial technique for personalizing these systems and reducing customer friction. However, existing QR models, trained on personal rephrases in history face a critical drawback - they are unable to reformulate unseen queries to unseen targets. To alleviate this, we present RecQR, a novel system based on collaborative filters, designed to reformulate unseen defective requests to target requests that a customer may never have requested for in the past. RecQR anticipates a customer’s future requests and rewrites them using state of the art, large-scale, collaborative filtering and query reformulation models. Based on experiments we find that it reduces errors by nearly 40% (relative) on the reformulated utterances.

2021

1. AAAI 2021

   Unsupervised Causal Knowledge Extraction from Text using Natural Language Inference.

   Manik Bhandari, Mark Feblowitz, Oktie Hassanzadeh, Kavitha Srinivas, and Shirin Sohrabi

   In Proceedings of the Thirty Fifth Conference on Artificial Intelligence (AAAI-21) Student Abstract, Nov 2021

   Abs HTML PDF

   In this paper, we address the problem of extracting causal knowledge from text documents in a weakly supervised manner. We target use cases in decision support and risk management, where causes and effects are general phrases without any constraints. We present a method called CaKnowLI which only takes as input the text corpus and extracts a high-quality collection of cause-effect pairs in an automated way. We approach this problem using state-of-the-art natural language understanding techniques based on pre-trained neural models for Natural Language Inference (NLI). Finally, we evaluate the proposed method on existing and new benchmark data sets.

2020

1. EMNLP 2020

   Re-evaluating Evaluation in Text Summarization

   Manik Bhandari, Pranav Narayan Gour, Atabak Ashfaq, Pengfei Liu, and Graham Neubig

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020

   Abs HTML PDF

   Automated evaluation metrics as a stand-in for manual evaluation are an essential part of the development of text-generation tasks such as text summarization. However, while the field has progressed, our standard metrics have not – for nearly 20 years ROUGE has been the standard evaluation in most summarization papers. In this paper, we make an attempt to re-evaluate the evaluation method for text summarization: assessing the reliability of automatic metrics using top-scoring system outputs, both abstractive and extractive, on recently popular datasets for both system-level and summary-level evaluation settings. We find that conclusions about evaluation metrics on older datasets do not necessarily hold on modern datasets and systems. We release a dataset of human judgments that are collected from 25 top-scoring neural summarization systems (14 abstractive and 11 extractive).

2. COLING 2020

   Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics

   Manik Bhandari, Pranav Narayan Gour, Atabak Ashfaq, and Pengfei Liu

   In Proceedings of the 28th International Conference on Computational Linguistics, Dec 2020

   Abs HTML PDF

   In text summarization, evaluating the efficacy of automatic metrics without human judgments has become recently popular. One exemplar work (Peyrard, 2019) concludes that automatic metrics strongly disagree when ranking high-scoring summaries. In this paper, we revisit their experiments and find that their observations stem from the fact that metrics disagree in ranking summaries from any narrow scoring range. We hypothesize that this may be because summaries are similar to each other in a narrow scoring range and are thus, difficult to rank. Apart from the width of the scoring range of summaries, we analyze three other properties that impact inter-metric agreement - Ease of Summarization, Abstractiveness, and Coverage.

2019

1. AISTATS 2019

   Confidence-based Graph Convolutional Networks for Semi-Supervised Learning.

   Shikhar Vashishth, Prateek Yadav, Manik Bhandari, and Partha Talukdar

   In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Nov 2019

   Abs HTML PDF

   Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the nodes in the graph. Recently, Graph Convolutional Networks (GCNs) have achieved impressive performance on the graph-based SSL task. In addition to label scores, it is also desirable to have confidence scores associated with them. Unfortunately, confidence estimation in the context of GCN has not been previously explored. We fill this important gap in this paper and propose ConfGCN, which estimates labels scores along with their confidences jointly in GCN-based setting. ConfGCN uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Through extensive analysis and experiments on standard benchmarks, we find that ConfGCN is able to outperform state-of-the-art baselines. We have made ConfGCN’s source code available to encourage reproducible research.

2. NAACL 2019

   Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation

   Ashutosh Kumar, Satwik Bhattamishra, Manik Bhandari, and Partha Talukdar

   In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Jun 2019

   Abs DOI HTML PDF

   Inducing diversity in the task of paraphrasing is an important problem in NLP with applications in data augmentation and conversational agents. Previous paraphrasing approaches have mainly focused on the issue of generating semantically similar paraphrases while paying little attention towards diversity. In fact, most of the methods rely solely on top-k beam search sequences to obtain a set of paraphrases. The resulting set, however, contains many structurally similar sentences. In this work, we focus on the task of obtaining highly diverse paraphrases while not compromising on paraphrasing quality. We provide a novel formulation of the problem in terms of monotone submodular function maximization, specifically targeted towards the task of paraphrasing. Additionally, we demonstrate the effectiveness of our method for data augmentation on multiple tasks such as intent classification and paraphrase recognition. In order to drive further research, we have made the source code available.

3. ACL 2019

   Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

   Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai, Chiranjib Bhattacharyya, and Partha Talukdar

   In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Jul 2019

   Abs DOI HTML PDF

   Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.