Santu Karmaker

Faria Binte Kader, Mohtasim Hadi Rafi, Shah Wasif Sajjad et al.

Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight into whether current LLMs can handle structurally distinct low-resource musical traditions. We present the first systematic evaluation of LLM competence in South Asian classical music, a tradition governed by raga, tala-based melodic constraints that impose fundamentally different structural principles from Western harmony-driven music. We ground our evaluation in Hindustani classical theory and Bengali classical forms, including Rabindra and Nazrul Sangeet -- representative low-resource traditions within South Asian classical music. For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning, evaluating 33 LLMs where frontier models such as Gemini 2.5 Pro achieve 85-90% accuracy, while most open-source models remain in the 23-40% range. For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time. These results reveal that structural validity and stylistic faithfulness in music generation are distinct objectives and highlight an open challenge for culturally grounded music modeling.

Adam Bawatneh, Sagar Sapkota, Amrit Singh Bedi et al.

Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, particularly in scenarios involving divergent, evolving, or mistaken beliefs. In order to address this research gap, we introduce OmniToM, a benchmark that directly evaluates these representations by requiring explicit modeling of belief structures for all relevant actors within a narrative. These structures are composed of belief propositions: minimal statements of what an actor takes to be true about the world or another actor's mental state, allowing knowledge, intentions, emotions, and false beliefs to be analyzed in a common format. Models are evaluated in two stages: Stage 1: Belief Extraction, which extracts from the story the beliefs relevant to its social dynamics, and Stage 2: Belief Labeling, which assigns each belief a seven-dimensional schema label covering recursive order, truth status, knowledge access, explicitness, content type, mental source, and context. Built from 895 stories from the existing ToMBench story corpus and augmented with 22,343 labeled belief propositions, OmniToM uses a human-calibrated LLM-assisted annotation pipeline. Across diverse models in zero-shot evaluation, OmniToM reveals an actor-specific belief-tracking bottleneck: current LLMs struggle with the knowledge-access and representational decisions required to transform narrative facts into actors' beliefs and shared mental states.

Eshgin Hasanov, Md Mahadi Hassan Sibat, Santu Karmaker et al.

Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks primarily focus on predicting program properties tied to specific inputs (e.g., code coverage, program outputs). As a result, they provide a narrow view of dynamic code reasoning and are prone to data contamination. We argue that understanding program execution requires evaluating its inherent duality through two complementary reasoning tasks: (i) predicting a program's observed behavior for a given input, and (ii) inferring how the input must be mutated toward a specific behavioral objective. Both tasks jointly probe a model's causal understanding of execution flow. We instantiate this duality in DexBench, a benchmark comprising 445 paired instances, and evaluate 13 LLMs. Our results demonstrate that dual-path reasoning provides a robust and discriminative proxy for dynamic code understanding.

Mousumi Akter, Santu Karmaker

The ROUGE metric is commonly used to evaluate extractive summarization task, but it has been criticized for its lack of semantic awareness and its ignorance about the ranking quality of the extractive summarizer. Previous research has introduced a gain-based automated metric called Sem-nCG that addresses these issues, as it is both rank and semantic aware. However, it does not consider the amount of redundancy present in a model summary and currently does not support evaluation with multiple reference summaries. It is essential to have a model summary that balances importance and diversity, but finding a metric that captures both of these aspects is challenging. In this paper, we propose a redundancy-aware Sem-nCG metric and demonstrate how the revised Sem-nCG metric can be used to evaluate model summaries against multiple references as well which was missing in previous research. Experimental results demonstrate that the revised Sem-nCG metric has a stronger correlation with human judgments compared to the previous Sem-nCG metric and traditional ROUGE and BERTScore metric for both single and multiple reference scenarios.

Abdullah Khan Zehady, Shubhashis Roy Dipta, Naymul Islam et al.

Bangla is a language spoken by approximately 240 million native speakers and around 300 million people worldwide. Despite being the 5th largest spoken language in the world, Bangla is still a "low-resource" language, and existing pretrained language models often struggle to perform well on Bangla Language Processing (BLP) tasks. This paper addresses this gap by: (1) introducing two high-quality translated Bangla-instruction datasets totaling 224k samples - Bangla-Orca (172k) and Bangla-Alpaca (52k); and (2) leveraging these datasets to develop BanglaLlama, an open-source family of Bangla-specific LLMs, consisting of five base and instruct variants. We present our methodology, two large datasets, and comprehensive benchmarking results showcasing the effectiveness of our dataset and model on multiple benchmarks. We believe our proposed datasets and models will serve as the new standard baseline for future research focused on this widely spoken yet "low-resource" language.

Yogesh Agrawal, Aniruddha Dutta, Md Mahadi Hasan et al.

Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with the advancement of Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning over how company stocks trade in the market or their interactions with fundamentals. To take advantage of the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence.

R. Alexander Knipper, Indrani Dey, Souvika Sarkar et al.

Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.

Yash Mahajan, Matthew Freestone, Sathyanarayanan Aakur 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.

Md. Najib Hasan, Mohammad Fakhruddin Babar, Souvika Sarkar et al.

Open Large Language Model (LLM) benchmarks, such as HELM and BIG-bench, offer standardized, transparent protocols that facilitate the fair comparison, reproducibility, and iterative advancement of Language Models (LMs). However, their openness also introduces critical and underexplored pitfalls. This study exposes these weaknesses by systematically constructing ``cheating'' models -- smaller variants of BART, T5, and GPT-2 fine-tuned directly on public test sets -- which achieve top rankings on a prominent open, holistic benchmark (HELM) despite poor generalization and limited practical utility. Our findings underscore three key insights: \ca high leaderboard performance on open benchmarks may not always reflect real-world effectiveness; \cb private or dynamic benchmarks must complement open evaluations to safeguard integrity; and \cc a fundamental reevaluation of current benchmarking practices is essential to ensure robust and trustworthy LM assessments.

Leo Kampen, Carlos Rabat Villarreal, Louis Yu et al.

In this paper, we conducted a Multi-Perspective Comparative Narrative Analysis (CNA) on three prominent LLMs: GPT-3.5, PaLM2, and Llama2. We applied identical prompts and evaluated their outputs on specific tasks, ensuring an equitable and unbiased comparison between various LLMs. Our study revealed that the three LLMs generated divergent responses to the same prompt, indicating notable discrepancies in their ability to comprehend and analyze the given task. Human evaluation was used as the gold standard, evaluating four perspectives to analyze differences in LLM performance.

R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang et al. · allen-ai, deepmind

As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases. Extensively studied in the field of psychology, cognitive biases appear as systematic distortions commonly observed in human judgments. This paper presents a large-scale evaluation of eight well-established cognitive biases across 45 LLMs, analyzing over 2.8 million LLM responses generated through controlled prompt variations. To achieve this, we introduce a novel evaluation framework based on multiple-choice tasks, hand-curate a dataset of 220 decision scenarios targeting fundamental cognitive biases in collaboration with psychologists, and propose a scalable approach for generating diverse prompts from human-authored scenario templates. Our analysis shows that LLMs exhibit bias-consistent behavior in 17.8-57.3% of instances across a range of judgment and decision-making contexts targeting anchoring, availability, confirmation, framing, interpretation, overattribution, prospect theory, and representativeness biases. We find that both model size and prompt specificity play a significant role on bias susceptibility as follows: larger size (>32B parameters) can reduce bias in 39.5% of cases, while higher prompt detail reduces most biases by up to 14.9%, except in one case (Overattribution), which is exacerbated by up to 8.8%.

Sagar Sapkota, Mohammad Saqib Hasan, Mubarak Shah et al.

Multi-party Conversational Agents (MPCAs) are systems designed to engage in dialogue with more than two participants simultaneously. Unlike traditional two-party agents, designing MPCAs faces additional challenges due to the need to interpret both utterance semantics and social dynamics. This survey explores recent progress in MPCAs by addressing three key questions: 1) Can agents model each participants' mental states? (State of Mind Modeling); 2) Can they properly understand the dialogue content? (Semantic Understanding); and 3) Can they reason about and predict future conversation flow? (Agent Action Modeling). We review methods ranging from classical machine learning to Large Language Models (LLMs) and multi-modal systems. Our analysis underscores Theory of Mind (ToM) as essential for building intelligent MPCAs and highlights multi-modal understanding as a promising yet underexplored direction. Finally, this survey offers guidance to future researchers on developing more capable MPCAs.

Souvika Sarkar, Md. Najib Hasan, Santu Karmaker

Bangla, a language spoken by over 300 million native speakers and ranked as the sixth most spoken language worldwide, presents unique challenges in natural language processing (NLP) due to its complex morphological characteristics and limited resources. While recent Large Decoder Based models (LLMs), such as GPT, LLaMA, and DeepSeek, have demonstrated excellent performance across many NLP tasks, their effectiveness in Bangla remains largely unexplored. In this paper, we establish the first benchmark comparing decoder-based LLMs with classic encoder-based models for Zero-Shot Multi-Label Classification (Zero-Shot-MLC) task in Bangla. Our evaluation of 32 state-of-the-art models reveals that, existing so-called powerful encoders and decoders still struggle to achieve high accuracy on the Bangla Zero-Shot-MLC task, suggesting a need for more research and resources for Bangla NLP.

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.