Papers by Koustava Goswami
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Prior research addresses generating attributions alongside responses in open domains, either per sentence or per paragraph. |
| Approach: | They propose a method to decompose generated answers for attribution using template-based in-context learning. |
| Outcome: | The proposed approach enhances the semantic understanding of abstractive and extractive answers. |
Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Long document question answering requires locating relevant paragraphs within a document to answer a question. |
| Approach: | They propose to exploit the discourse structure commonly found in documents to create a condensed representation of the document, enabling a more comprehensive understanding and analysis of relationships between different parts. |
| Outcome: | The proposed approach retains 99.6% of the best zero-shot approach's performance while processing only 26% of tokens used by the best approach in the information seeking evidence retrieval setup. |
An Audit on the Perspectives and Challenges of Hallucinations in NLP (2024.emnlp-main)
Copied to clipboard
Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs, Mukund Srinath, Koustava Goswami, Sarah Rajtmajer, Shomir Wilson
| Challenge: | 103 peer-reviewed publications on hallucination in large language models (LLMs) are characterized by a lack of agreement with the term ‘hallucination’ in the field of NLP. |
| Approach: | They examine 103 peer-reviewed publications on hallucination in large language models (LLMs) and conduct a survey with 171 practitioners from the field of NLP and AI to capture varying perspectives on halllucination. |
| Outcome: | The findings highlight the need for explicit definitions and frameworks outlining hallucination within NLP and highlight potential challenges. |
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs (2025.naacl-long)
Copied to clipboard
Anirudh Phukan, Divyansh Divyansh, Harshit Kumar Morj, Vaishnavi Vaishnavi, Apoorv Saxena, Koustava Goswami
| Challenge: | Large Multimodal Models are plagued by hallucinations that limit their reliability and adoption. |
| Approach: | They propose a method that leverages contextual token embeddings from LMMs to detect hallucinations. |
| Outcome: | The proposed method improves hallucination detection and grounding across diverse categories while excelling in tasks requiring contextual understanding. |
Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models (2025.coling-main)
Copied to clipboard
Sofia Jamil, Bollampalli Areen Reddy, Raghvendra Kumar, Sriparna Saha, Joseph K. J, Koustava Goswami
| Challenge: | Poems are a distinct form of literature, with meanings that transcend beyond the literal words. |
| Approach: | They propose a framework to generate images that visually represent the meanings of poems using prompt tuning and a PoeKey algorithm to extract emotions, visual elements, and themes from poems. |
| Outcome: | The proposed framework generates images that visually represent the meanings of poems and their images. |
Subjective Behaviors and Preferences in LLM: Language of Browsing (2025.emnlp-main)
Copied to clipboard
Sai Sundaresan, Harshita Chopra, Atanu R. Sinha, Koustava Goswami, Nagasai Saketh Naidu, Raghav Karan, N Anushka
| Challenge: | Large Language Models (LLMs) fuel expectations that a single trained model can effectively align with preferences of myriad users for a given task within a domain. |
| Approach: | They introduce clusterwise LM training, HeTLM, appropriate for subjective behaviors . authors say small LM outperforms large pretrained LMs; heterogeneous cluster specific set of parameters outperformed single LM . |
| Outcome: | The proposed model outperforms large pretrained or finetuned models in the domain of subjective behavior and preferences. |
Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used for question answering . lack of explicit references or attributions hinders ability to verify accuracy of answers . |
| Approach: | They propose a method for attribution in contextual question answering . they use hidden state representations of large language models to identify copied segments . |
| Outcome: | The proposed method performs better than GPT-4 at identifying verbatim copied segments in LLM generations and attributing these segments to their source. |
Cross-lingual Sentence Embedding using Multi-Task Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual sentence embedding models require large parallel corpora to learn efficiently, limiting their scope. |
| Approach: | They propose a sentence embedding framework based on an unsupervised loss function . they capture semantic similarity and relatedness between sentences using a multi-task loss function. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on STS, BUCC and Tatoeba benchmarks and on a monolingual benchmark. |
SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent work shows promising results when prompting pre-trained language models, but in low-resource domains, the domain gap between the pre-training data and the downstream task is too large. |
| Approach: | They propose a method for prompting pre-trained language models using domain-specific keywords with a trainable gated prompt. |
| Outcome: | The proposed prompting method outperforms state-of-the-art prompting methods on three text classification benchmarks and shows that it reduces the need for domain-specific language model pre-training. |
Unsupervised Deep Language and Dialect Identification for Short Texts (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for identifying closely related short texts are unsupervised . however, performance is poor for unsupervised methods for short texts . |
| Approach: | They propose a method which can learn sentence embeddings and cluster assignments from short texts. |
| Outcome: | The proposed method outperforms state-of-the-art methods in supervised settings . it can learn sentence embeddings and cluster assignments from short texts . |
Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing work on attribution of answer text to source document is limited . existing systems are prone to generating answers lacking sufficient grounding to knowledge sources . |
| Approach: | They propose to use existing datasets to assess the strengths and weaknesses of existing systems for this task. |
| Outcome: | The proposed system is based on retrieval-based and textual entailment-based optimal selection attribution systems. |
Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models (2026.eacl-long)
Copied to clipboard
Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami, Ryan A. Rossi, Varun Manjunatha, Roshan Santhosh, Ruiyi Zhang, Soheil Feizi, Nedim Lipka
| Challenge: | Existing methods for extractive QA struggle in multi-hop, abstractive, and semi-extractive settings. |
| Approach: | They propose a method that prompts models to produce answer decompositions as intermediate reasoning steps. |
| Outcome: | The proposed method outperforms existing methods and matches or exceeds state-of-the-art frontier models. |
Suggest me a movie for tonight: Leveraging Knowledge Graphs for Conversational Recommendation (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies show that knowledge graphs are incomplete since they do not contain all factual information present on the web. |
| Approach: | They propose to use knowledge graphs to improve the performance of conversational recommender systems by incorporating pre-trained embeddings from subgraphs and positional embeddments into their models. |
| Outcome: | The proposed method improves by 5.62% over the state-of-the-art method on multiple metrics on the recommendation task. |
Do It Yourself (DIY): Modifying Images for Poems in a Zero-Shot Setting Using Weighted Prompt Manipulation (2025.emnlp-main)
Copied to clipboard
| Challenge: | a novel method to enhance imagery in poetic language is proposed . weighted prompt manipulation is a new approach to enhance poetry images . current diffusion models struggle to interpret metaphorical language, symbolism, and nuanced themes. |
| Approach: | They propose a weighted prompt manipulation technique that modifies attention weights and text embeddings within diffusion models to enhance or suppress specific words' influence in the final generated image. |
| Outcome: | The proposed technique enhances or suppresses the influence of specific words in the final generated image, leading to semantically richer and more contextually accurate visualizations. |
Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to cognate detection focus on orthographic, phonetic or contextual models, which under-perform for most under-resourced languages. |
| Approach: | They propose a language-agnostic weakly-supervised deep cognate detection framework for under-resourced languages using morphological knowledge from closely related languages. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on cognate detection datasets across languages and can be extended to a wide range of languages from any language family. |