Related papers: NAIPv2: Debiased Pairwise Learning for Efficient P…
Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists. With the abundance of recent natural language processing advances, the information…
Inverted file structure is a common technique for accelerating dense retrieval. It clusters documents based on their embeddings; during searching, it probes nearby clusters w.r.t. an input query and only evaluates documents within them by…
Peer review assignment algorithms aim to match research papers to suitable expert reviewers, working to maximize the quality of the resulting reviews. A key challenge in designing effective assignment policies is evaluating how changes to…
Pairwise comparison data arise in many domains with subjective assessment experiments, for example in image and video quality assessment. In these experiments observers are asked to express a preference between two conditions. However, many…
Students opting for Engineering as their discipline is increasing rapidly. But due to various factors and inappropriate primary education in India, failure rates are high. Students are unable to excel in core engineering because of complex…
We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…
Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…
Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…
Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…
Neural machine translation (NMT) systems typically employ maximum a posteriori (MAP) decoding to select the highest-scoring translation from the distribution mass. However, recent evidence highlights the inadequacy of MAP decoding, often…
It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich…
Linguistic bias in online news and social media is widespread but difficult to measure. Yet, its identification and quantification remain difficult due to subjectivity, context dependence, and the scarcity of high-quality gold-label…
Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. FAST$^2$ is a novel tool for reducing the effort required for conducting literature reviews by assisting the…
Recent advances in large language models (LLMs) have demonstrated the effectiveness of Iterative Self-Improvement (ISI) techniques. However, continuous training on self-generated data leads to reduced output diversity, a limitation…
Peer review is the method employed by the scientific community for evaluating research advancements. In the field of cybersecurity, the practice of double-blind peer review is the de-facto standard. This paper touches on the holy grail of…
Although click data is widely used in search systems in practice, so far the inherent bias, most notably position bias, has prevented it from being used in training of a ranker for search, i.e., learning-to-rank. Recently, a number of…
Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based…
In this paper, we consider large-scale ranking problems where one is given a set of (possibly non-redundant) pairwise comparisons and the underlying ranking explained by those comparisons is desired. We show that stochastic gradient descent…
Obtaining high certainty in predictive models is crucial for making informed and trustworthy decisions in many scientific and engineering domains. However, extensive experimentation required for model accuracy can be both costly and…
Information retrieval (IR) and recommender systems (RS) have been employed for addressing search tasks executed during literature review and the overall scholarly communication lifecycle. Majority of the studies have concentrated on…