arXiv subjects

Tanmoy Chakraborty

Publications and source records attributed to Tanmoy Chakraborty.

At least 109 records · Page 6Linked to original sources

arXiv2024

Temporally Consistent Factuality Probing for Large Language Models

The prolific use of Large Language Models (LLMs) as an alternate knowledge base requires them to be factually consistent, necessitating both correctness and consistency traits for paraphrased queries. Recently, significant attempts have been made to benchmark datasets and metrics to evaluate LLMs for these traits. However, structural simplicity (subject-relation-object) and contemporary association in their query formulation limit the broader definition of factuality and consistency. In this study, we introduce TeCFaP, a novel Temporally Consistent Factuality Probe task to expand the consistent factuality probe in the temporal dimension. To this end, we propose TEMP-COFAC, a high-quality dataset of prefix-style English query paraphrases. Subsequently, we extend the definitions of existing metrics to represent consistent factuality across temporal dimension. We experiment with a diverse set of LLMs and find most of them performing poorly on TeCFaP. Next, we propose a novel solution CoTSeLF (Consistent-Time-Sensitive Learning Framework) combining multi-task instruction tuning (MT-IT) with consistent-time-sensitive reinforcement learning (CTSRL) to improve temporally consistent factuality in LLMs. Our experiments demonstrate the efficacy of CoTSeLF over several baselines.

cs.CL↗

arXiv2024

Mechanistic Behavior Editing of Language Models

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious features learned from noisy data hinder their generalizability. Supervised finetuning can introduce task specificity, but introduce data inefficiency. Prior studies indicate that (i) noisy neural circuitries coexist with generalizable ones within LLMs, and (ii) finetuning typically enhances (or suppresses) existing abilities without introducing newer ones. Building upon these, we propose TaRot, a novel method for task adaptation. TaRot intervenes in the neural circuitries using learnable rotation matrices that are optimized using Bayesian Optimization, on labelled samples in the order of standard few-shot prompting examples. Experiments on multiple classification and generation tasks using LLMs of varying sizes reveal the efficacy of TaRot, improving upon both zero- as well as few-shot performance, with average improvements (across models and tasks) of 23.81% and 11.15%, respectively. The source code is available at https://github.com/joykirat18/TaRot

cs.CL↗

arXiv2024

POSIX: A Prompt Sensitivity Index For Large Language Models

Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent outputs in response to minor variations in the prompts, such as spelling errors, alteration of wording or the prompt template. However, while assessing the quality of an LLM, the focus often tends to be solely on its performance on downstream tasks, while very little to no attention is paid to prompt sensitivity. To fill this gap, we propose POSIX - a novel PrOmpt Sensitivity IndeX as a reliable measure of prompt sensitivity, thereby offering a more comprehensive evaluation of LLM performance. The key idea behind POSIX is to capture the relative change in loglikelihood of a given response upon replacing the corresponding prompt with a different intent-preserving prompt. We provide thorough empirical evidence demonstrating the efficacy of POSIX in capturing prompt sensitivity and subsequently use it to measure and thereby compare prompt sensitivity of various open-source LLMs. We find that merely increasing the parameter count or instruction tuning does not necessarily reduce prompt sensitivity whereas adding some few-shot exemplars, even just one, almost always leads to significant decrease in prompt sensitivity. We also find that alterations to prompt template lead to the highest sensitivity in the case of MCQ type tasks, whereas paraphrasing results in the highest sensitivity in open-ended generation tasks. The code for reproducing our results is open-sourced at https://github.com/kowndinya-renduchintala/POSIX.

cs.CL↗

arXiv2024

Hate Personified: Investigating the role of LLMs in content moderation

For subjective tasks such as hate detection, where people perceive hate differently, the Large Language Model's (LLM) ability to represent diverse groups is unclear. By including additional context in prompts, we comprehensively analyze LLM's sensitivity to geographical priming, persona attributes, and numerical information to assess how well the needs of various groups are reflected. Our findings on two LLMs, five languages, and six datasets reveal that mimicking persona-based attributes leads to annotation variability. Meanwhile, incorporating geographical signals leads to better regional alignment. We also find that the LLMs are sensitive to numerical anchors, indicating the ability to leverage community-based flagging efforts and exposure to adversaries. Our work provides preliminary guidelines and highlights the nuances of applying LLMs in culturally sensitive cases.

cs.CL↗

arXiv2024

Are Large Language Models In-Context Personalized Summarizers? Get an iCOPERNICUS Test Done!

Large Language Models (LLMs) have succeeded considerably in In-Context-Learning (ICL) based summarization. However, saliency is subject to the users' specific preference histories. Hence, we need reliable In-Context Personalization Learning (ICPL) capabilities within such LLMs. For any arbitrary LLM to exhibit ICPL, it needs to have the ability to discern contrast in user profiles. A recent study proposed a measure for degree-of-personalization called EGISES for the first time. EGISES measures a model's responsiveness to user profile differences. However, it cannot test if a model utilizes all three types of cues provided in ICPL prompts: (i) example summaries, (ii) user's reading histories, and (iii) contrast in user profiles. To address this, we propose the iCOPERNICUS framework, a novel In-COntext PERsonalization learNIng sCrUtiny of Summarization capability in LLMs that uses EGISES as a comparative measure. As a case-study, we evaluate 17 state-of-the-art LLMs based on their reported ICL performances and observe that 15 models' ICPL degrades (min: 1.6%; max: 3.6%) when probed with richer prompts, thereby showing lack of true ICPL.

cs.CL↗

arXiv2024

Large Language Model Predicts Above Normal All India Summer Monsoon Rainfall in 2024

Reliable prediction of the All India Summer Monsoon Rainfall (AISMR) is pivotal for informed policymaking for the country, impacting the lives of billions of people. However, accurate simulation of AISMR has been a persistent challenge due to the complex interplay of various muti-scale factors and the inherent variability of the monsoon system. This research focuses on adapting and fine-tuning the latest LLM model, PatchTST, to accurately predict AISMR with a lead time of three months. The fine-tuned PatchTST model, trained with historical AISMR data, the Niño3.4 index, and categorical Indian Ocean Dipole values, outperforms several popular neural network models and statistical models. This fine-tuned LLM model exhibits an exceptionally low RMSE percentage of 0.07% and a Spearman correlation of 0.976. This is particularly impressive, since it is nearly 80% more accurate than the best-performing NN models. The model predicts an above-normal monsoon for the year 2024, with an accumulated rainfall of 921.6 mm in the month of June-September for the entire country.

cs.AI↗

arXiv2024

Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization

In mental health counseling, condensing dialogues into concise and relevant summaries (aka counseling notes) holds pivotal significance. Large Language Models (LLMs) exhibit remarkable capabilities in various generative tasks; however, their adaptation to domain-specific intricacies remains challenging, especially within mental health contexts. Unlike standard LLMs, mental health experts first plan to apply domain knowledge in writing summaries. Our work enhances LLMs' ability by introducing a novel planning engine to orchestrate structuring knowledge alignment. To achieve high-order planning, we divide knowledge encapsulation into two major phases: (i) holding dialogue structure and (ii) incorporating domain-specific knowledge. We employ a planning engine on Llama-2, resulting in a novel framework, PIECE. Our proposed system employs knowledge filtering-cum-scaffolding to encapsulate domain knowledge. Additionally, PIECE leverages sheaf convolution learning to enhance its understanding of the dialogue's structural nuances. We compare PIECE with 14 baseline methods and observe a significant improvement across ROUGE and Bleurt scores. Further, expert evaluation and analyses validate the generation quality to be effective, sometimes even surpassing the gold standard. We further benchmark PIECE with other LLMs and report improvement, including Llama-2 (+2.72%), Mistral (+2.04%), and Zephyr (+1.59%), to justify the generalizability of the planning engine.

cs.CL↗

arXiv2024

Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators

Large Language Models (LLMs) and AI assistants driven by these models are experiencing exponential growth in usage among both expert and amateur users. In this work, we focus on evaluating the reliability of current LLMs as science communicators. Unlike existing benchmarks, our approach emphasizes assessing these models on scientific questionanswering tasks that require a nuanced understanding and awareness of answerability. We introduce a novel dataset, SCiPS-QA, comprising 742 Yes/No queries embedded in complex scientific concepts, along with a benchmarking suite that evaluates LLMs for correctness and consistency across various criteria. We benchmark three proprietary LLMs from the OpenAI GPT family and 13 open-access LLMs from the Meta Llama-2, Llama-3, and Mistral families. While most open-access models significantly underperform compared to GPT-4 Turbo, our experiments identify Llama-3-70B as a strong competitor, often surpassing GPT-4 Turbo in various evaluation aspects. We also find that even the GPT models exhibit a general incompetence in reliably verifying LLM responses. Moreover, we observe an alarming trend where human evaluators are deceived by incorrect responses from GPT-4 Turbo.

cs.CL↗

arXiv2024

Self-similarity of temporal interaction networks arises from hyperbolic geometry with time-varying curvature

The self-similarity of complex systems has been studied intensely across different domains due to its potential applications in system modeling, complexity analysis, etc., as well as for deep theoretical interest. Existing studies rely on scale transformations conceptualized over either a definite geometric structure of the system (very often realized as length-scale transformations) or purely temporal scale transformations. However, many physical and social systems are observed as temporal interactions among agents without any definitive geometry. Yet, one can imagine the existence of an underlying notion of distance as the interactions are mostly localized. Analysing only the time-scale transformations over such systems would uncover only a limited aspect of the complexity. In this work, we propose a novel technique of scale transformation that dissects temporal interaction networks under spatio-temporal scales, namely, flow scales. Upon experimenting with multiple social and biological interaction networks, we find that many of them possess a finite fractal dimension under flow-scale transformation. Finally, we relate the emergence of flow-scale self-similarity to the latent geometry of such networks. We observe strong evidence that justifies the assumption of an underlying, variable-curvature hyperbolic geometry that induces self-similarity of temporal interaction networks. Our work bears implications for modeling temporal interaction networks at different scales and uncovering their latent geometric structures.

physics.soc-ph↗

arXiv2024

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models

While recent large language models (LLMs) demonstrate remarkable abilities in responding to queries in diverse languages, their ability to handle long multilingual contexts is unexplored. As such, a systematic evaluation of the long-context capabilities of LLMs in multilingual settings is crucial, specifically in the context of information retrieval. To address this gap, we introduce the MultiLingual Needle-in-a-Haystack (MLNeedle) test, designed to assess a model's ability to retrieve relevant information (the needle) from a collection of multilingual distractor texts (the haystack). This test serves as an extension of the multilingual question-answering task, encompassing both monolingual and cross-lingual retrieval. We evaluate four state-of-the-art LLMs on MLNeedle. Our findings reveal that model performance can vary significantly with language and needle position. Specifically, we observe that model performance is the lowest when the needle is (i) in a language outside the English language family and (ii) located in the middle of the input context. Furthermore, although some models claim a context size of $8k$ tokens or greater, none demonstrate satisfactory cross-lingual retrieval performance as the context length increases. Our analysis provides key insights into the long-context behavior of LLMs in multilingual settings to guide future evaluation protocols. To our knowledge, this is the first study to investigate the multilingual long-context behavior of LLMs.

cs.CL↗

arXiv2024

Crowd Intelligence for Early Misinformation Prediction on Social Media

Misinformation spreads rapidly on social media, causing serious damage by influencing public opinion, promoting dangerous behavior, or eroding trust in reliable sources. It spreads too fast for traditional fact-checking, stressing the need for predictive methods. We introduce CROWDSHIELD, a crowd intelligence-based method for early misinformation prediction. We hypothesize that the crowd's reactions to misinformation reveal its accuracy. Furthermore, we hinge upon exaggerated assertions/claims and replies with particular positions/stances on the source post within a conversation thread. We employ Q-learning to capture the two dimensions -- stances and claims. We utilize deep Q-learning due to its proficiency in navigating complex decision spaces and effectively learning network properties. Additionally, we use a transformer-based encoder to develop a comprehensive understanding of both content and context. This multifaceted approach helps ensure the model pays attention to user interaction and stays anchored in the communication's content. We propose MIST, a manually annotated misinformation detection Twitter corpus comprising nearly 200 conversation threads with more than 14K replies. In experiments, CROWDSHIELD outperformed ten baseline systems, achieving an improvement of ~4% macro-F1 score. We conduct an ablation study and error analysis to validate our proposed model's performance. The source code and dataset are available at https://github.com/LCS2-IIITD/CrowdShield.git.

cs.CL↗

arXiv2024

Independent fact-checking organizations exhibit a departure from political neutrality

Independent fact-checking organizations have emerged as the crusaders to debunk fake news. However, they may not always remain neutral, as they can be selective in the false news they choose to expose and in how they present the information. They can deviate from neutrality by being selective in what false news they debunk and how the information is presented. Prompting the now popular large language model, GPT-3.5, with journalistic frameworks, we establish a longitudinal measure (2018-2023) for political neutrality that looks beyond the left-right spectrum. Specified on a range of -1 to 1 (with zero being absolute neutrality), we establish the extent of negative portrayal of political entities that makes a difference in the readers' perception in the USA and India. Here, we observe an average score of -0.17 and -0.24 in the USA and India, respectively. The findings indicate how seemingly objective fact-checking can still carry distorted political views, indirectly and subtly impacting the perception of consumers of the news.

cs.SI↗

arXiv2024

Nonlinear interferometry-based metrology of magneto-optical properties at infrared wavelengths

Magneto-optical properties of materials are utilized in numerous applications both in scientific research and industries. The novel properties of these materials can be further investigated by performing metrology in the infrared wavelength range, thereby enriching their potential applications. However, current infrared metrology techniques can be challenging and resource-intensive due to the unavailability of suitable components. To address these challenges, we propose and demonstrate a set of measurements based on nonlinear interferometry, which allows us investigating magneto-optical properties of materials at infrared wavelength range by performing optical detection at the visible range. For a proof-of-principle study, we measure the Verdet constant of a bismuth-iron-garnet, over a spectral bandwidth of 600 nm in the near-IR range.

physics.optics↗

arXiv2024

Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks

Large Language Models (LLMs) have transformed NLP with their remarkable In-context Learning (ICL) capabilities. Automated assistants based on LLMs are gaining popularity; however, adapting them to novel tasks is still challenging. While colossal models excel in zero-shot performance, their computational demands limit widespread use, and smaller language models struggle without context. This paper investigates whether LLMs can generalize from labeled examples of predefined tasks to novel tasks. Drawing inspiration from biological neurons and the mechanistic interpretation of the Transformer architecture, we explore the potential for information sharing across tasks. We design a cross-task prompting setup with three LLMs and show that LLMs achieve significant performance improvements despite no examples from the target task in the context. Cross-task prompting leads to a remarkable performance boost of 107% for LLaMA-2 7B, 18.6% for LLaMA-2 13B, and 3.2% for GPT 3.5 on average over zero-shot prompting, and performs comparable to standard in-context learning. The effectiveness of generating pseudo-labels for in-task examples is demonstrated, and our analyses reveal a strong correlation between the effect of cross-task examples and model activation similarities in source and target input tokens. This paper offers a first-of-its-kind exploration of LLMs' ability to solve novel tasks based on contextual signals from different task examples.

cs.CL↗

arXiv2024

Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech

Employing language models to generate explanations for an incoming implicit hate post is an active area of research. The explanation is intended to make explicit the underlying stereotype and aid content moderators. The training often combines top-k relevant knowledge graph (KG) tuples to provide world knowledge and improve performance on standard metrics. Interestingly, our study presents conflicting evidence for the role of the quality of KG tuples in generating implicit explanations. Consequently, simpler models incorporating external toxicity signals outperform KG-infused models. Compared to the KG-based setup, we observe a comparable performance for SBIC (LatentHatred) datasets with a performance variation of +0.44 (+0.49), +1.83 (-1.56), and -4.59 (+0.77) in BLEU, ROUGE-L, and BERTScore. Further human evaluation and error analysis reveal that our proposed setup produces more precise explanations than zero-shot GPT-3.5, highlighting the intricate nature of the task.

cs.CL↗

arXiv2024

DPHGNN: A Dual Perspective Hypergraph Neural Networks

Message passing on hypergraphs has been a standard framework for learning higher-order correlations between hypernodes. Recently-proposed hypergraph neural networks (HGNNs) can be categorized into spatial and spectral methods based on their design choices. In this work, we analyze the impact of change in hypergraph topology on the suboptimal performance of HGNNs and propose DPHGNN, a novel dual-perspective HGNN that introduces equivariant operator learning to capture lower-order semantics by inducing topology-aware spatial and spectral inductive biases. DPHGNN employs a unified framework to dynamically fuse lower-order explicit feature representations from the underlying graph into the super-imposed hypergraph structure. We benchmark DPHGNN over eight benchmark hypergraph datasets for the semi-supervised hypernode classification task and obtain superior performance compared to seven state-of-the-art baselines. We also provide a theoretical framework and a synthetic hypergraph isomorphism test to express the power of spatial HGNNs and quantify the expressivity of DPHGNN beyond the Generalized Weisfeiler Leman (1-GWL) test. Finally, DPHGNN was deployed by our partner e-commerce company for the Return-to-Origin (RTO) prediction task, which shows ~7% higher macro F1-Score than the best baseline.

cs.LG↗

arXiv2024

Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems

Sharing ideas through communication with peers is the primary mode of human interaction. Consequently, extensive research has been conducted in the area of conversational AI, leading to an increase in the availability and diversity of conversational tasks, datasets, and methods. However, with numerous tasks being explored simultaneously, the current landscape of conversational AI becomes fragmented. Therefore, initiating a well-thought-out model for a dialogue agent can pose significant challenges for a practitioner. Towards highlighting the critical ingredients needed for a practitioner to design a dialogue agent from scratch, the current study provides a comprehensive overview of the primary characteristics of a dialogue agent, the supporting tasks, their corresponding open-domain datasets, and the methods used to benchmark these datasets. We observe that different methods have been used to tackle distinct dialogue tasks. However, building separate models for each task is costly and does not leverage the correlation among the several tasks of a dialogue agent. As a result, recent trends suggest a shift towards building unified foundation models. To this end, we propose UNIT, a UNified dIalogue dataseT constructed from conversations of existing datasets for different dialogue tasks capturing the nuances for each of them. We also examine the evaluation strategies used to measure the performance of dialogue agents and highlight the scope for future research in the area of conversational AI.

cs.CL↗

arXiv2024

MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing

Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects. Previous studies have analyzed memes in closed settings - detecting harm, applying semantic labels, and offering natural language explanations. To extend this research, we introduce MemeMQA, a multimodal question-answering framework aiming to solicit accurate responses to structured questions while providing coherent explanations. We curate MemeMQACorpus, a new dataset featuring 1,880 questions related to 1,122 memes with corresponding answer-explanation pairs. We further propose ARSENAL, a novel two-stage multimodal framework that leverages the reasoning capabilities of LLMs to address MemeMQA. We benchmark MemeMQA using competitive baselines and demonstrate its superiority - ~18% enhanced answer prediction accuracy and distinct text generation lead across various metrics measuring lexical and semantic alignment over the best baseline. We analyze ARSENAL's robustness through diversification of question-set, confounder-based evaluation regarding MemeMQA's generalizability, and modality-specific assessment, enhancing our understanding of meme interpretation in the multimodal communication landscape.

cs.CL↗