arXiv subjects

Rajarshi Haldar

Publications and source records attributed to Rajarshi Haldar.

6 recordsLinked to original sources

arXiv2026

Consistently Good vs. Occasionally Great: A Rubric for Open-Ended Feedback Quality from Humans and Machines

Providing high-quality feedback on student work is essential for learning, yet delivering such feedback at scale remains challenging. In this paper, we focus on feedback for open-ended short answer questions in introductory programming, with the goal of nudging students toward success on reattempts without revealing the correct answer. We develop a five-criteria rubric grounded in educational literature for evaluating feedback quality: (1) acknowledging correct portions of the student answer, (2) identifying at least one flaw (if present), (3) providing actionable guidance for improvement, (4) maintaining appropriate concealment of the answer, and (5) using an appropriate conversational tone. Using this rubric, we compare feedback generated by a frontier LLM (OpenAI o1) to feedback from nine teaching assistants across 90 student responses, with three researchers and an LLM independently scoring all feedback. Our results show that while one TA often produced the best feedback, the LLM demonstrated consistently higher average performance than TAs, as evaluated by humans. However, we also uncover significant self-preference bias when using LLMs to evaluate feedback quality: the LLM systematically rated its own outputs higher than human experts did. This bias, which research suggests persists even in cross-model evaluation, raises important methodological concerns for researchers employing LLM-based evaluation. We provide detailed characterization of both TA and LLM performance, analyze sources of variance in TA feedback quality, and discuss implications for deploying LLM-generated feedback in educational settings.

cs.CY↗

arXiv2025

Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks

As Natural Language Generation (NLG) continues to be widely adopted, properly assessing it has become quite difficult. Lately, using large language models (LLMs) for evaluating these generations has gained traction, as they tend to align more closely with human preferences than conventional n-gram or embedding-based metrics. In our experiments, we show that LLM judges have low intra-rater reliability in their assigned scores across different runs. This variance makes their ratings inconsistent, almost arbitrary in the worst case, making it difficult to measure how good their judgments actually are. We quantify this inconsistency across different NLG tasks and benchmarks and see if judicious use of LLM judges can still be useful following proper guidelines.

cs.CL↗

arXiv2024

Analyzing the Performance of Large Language Models on Code Summarization

Large language models (LLMs) such as Llama 2 perform very well on tasks that involve both natural language and source code, particularly code summarization and code generation. We show that for the task of code summarization, the performance of these models on individual examples often depends on the amount of (subword) token overlap between the code and the corresponding reference natural language descriptions in the dataset. This token overlap arises because the reference descriptions in standard datasets (corresponding to docstrings in large code bases) are often highly similar to the names of the functions they describe. We also show that this token overlap occurs largely in the function names of the code and compare the relative performance of these models after removing function names versus removing code structure. We also show that using multiple evaluation metrics like BLEU and BERTScore gives us very little additional insight since these metrics are highly correlated with each other.

cs.SE↗

arXiv2020

A Multi-Perspective Architecture for Semantic Code Search

The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective cross-lingual neural framework for code--text matching, inspired in part by a previous model for monolingual text-to-text matching, to capture both global and local similarities. Our experiments on the CoNaLa dataset show that our proposed model yields better performance on this cross-lingual text-to-code matching task than previous approaches that map code and text to a single joint embedding space.

cs.SE↗

arXiv2020

Cluster Aware Mobility Encounter Dataset Enlargement

The recent emerging fields in data processing and manipulation has facilitated the need for synthetic data generation. This is also valid for mobility encounter dataset generation. Synthetic data generation might be useful to run research-based simulations and also create mobility encounter models. Our approach in this paper is to generate a larger dataset by using a given dataset which includes the clusters of people. Based on the cluster information, we created a framework. Using this framework, we can generate a similar dataset that is statistically similar to the input dataset. We have compared the statistical results of our approach with the real dataset and an encounter mobility model generation technique in the literature. The results showed that the created datasets have similar statistical structure with the given dataset.

cs.NI↗

arXiv2018

CL Scholar: The ACL Anthology Knowledge Graph Miner

We present CL Scholar, the ACL Anthology knowledge graph miner to facilitate high-quality search and exploration of current research progress in the computational linguistics community. In contrast to previous works, periodically crawling, indexing and processing of new incoming articles is completely automated in the current system. CL Scholar utilizes both textual and network information for knowledge graph construction. As an additional novel initiative, CL Scholar supports more than 1200 scholarly natural language queries along with standard keyword-based search on constructed knowledge graph. It answers binary, statistical and list based natural language queries. The current system is deployed at http://cnerg.iitkgp.ac.in/aclakg. We also provide REST API support along with bulk download facility. Our code and data are available at https://github.com/CLScholar.

cs.DL↗