Papers by Kshitij Mishra
SD-E2: Semantic Exploration for Reasoning Under Token Budgets (2026.findings-eacl)
Copied to clipboard
| Challenge: | Small language models struggle with complex reasoning because exploration is expensive under tight compute budgets. |
| Approach: | They propose a framework that makes exploration explicit by optimizing semantic diversity in generated reasoning trajectories. |
| Outcome: | The proposed framework surpasses Qwen2.5-3B-Instruct and strong GRPO baselines on GSM8K and improves on the harder AIME benchmark to 13.28% vs. base 6.74%. |
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025.coling-industry)
Copied to clipboard
Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T. Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Barbosa Junior, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Nour Moustafa-Fahmy, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Hiep Nguyen, Sampo Pyysalo
| Challenge: | Pretrained language models are integral part of AI applications, but their high computational cost limits accessibility. |
| Approach: | They evaluate Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
| Outcome: | The proposed model outperforms existing models on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
ABLE: Personalized Disability Support with Politeness and Empathy Integration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Adaptive, Bespoke, Listen and Empathetic is a conversational support system for physical disabilities that tracks user personas and provides personalized support according to user person preferences. |
| Approach: | They propose a conversational support system that tracks user personas and integrates politeness and empathy levels into responses to ensure that support interactions are tailored to each user's characteristics and preferences. |
| Outcome: | The proposed system is based on a conversational dataset enriched with user profile annotations and tested on 84 users with physical disabilities. |
RPTCS: A Reinforced Persona-aware Topic-guiding Conversational System (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing systems that control concept transitions in a conversation lack a persona-aware topic transition dataset. |
| Approach: | They propose a persona-aware topic-guiding conversational system that leads the conversation to drift to a set of target concepts depending on the persona of the speaker and the context of the conversation. |
| Outcome: | The proposed system produces fluent responses with no useful information and is based on a conversational dataset with a human-in-loop only quality checks. |
MedLogic-AQA: Enhancing Medicare Question Answering with Abstractive Models Focusing on Logical Structures (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question-answering systems struggle to capture intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers. |
| Approach: | They propose a system that harnesses first-order logic-based rules extracted from context and questions to generate well-grounded answers. |
| Outcome: | The proposed system generates well-grounded answers based on first-order logic-based rules extracted from context and questions. |
e-THERAPIST: I suggest you to cultivate a mindset of positivity and nurture uplifting thoughts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing mental health workforce is struggling to meet the needs adequately. |
| Approach: | They propose a novel polite interpersonal psychotherapy dialogue system that is annotated at two levels: dialogue-level and utterance-level. |
| Outcome: | The proposed system can address depression, anxiety, schizophrenia and other mental health issues. |
PAL to Lend a Helping Hand: Towards Building an Emotion Adaptive Polite and Empathetic Counseling Conversational Agent (2023.acl-long)
Copied to clipboard
| Challenge: | The social stigma associated with mental illness prevents individuals from addressing their issues and getting assistance. |
| Approach: | They propose to build a Polite and empAthetic conversational agent PAL to lay down the counseling support to substance addicts and crime victims. |
| Outcome: | The proposed agent is scalable and can be easily modified with different modules of preference models as per need. |
PEPDS: A Polite and Empathetic Persuasive Dialogue System for Charity Donation (2022.coling-1)
Copied to clipboard
| Challenge: | Empathy plays a crucial role in mediating the persuasive effects as it evokes cognitive and emotional processing conducive to persuasion. |
| Approach: | They propose to use a maximum likelihood estimate loss based model to design an efficient reward function consisting of five sub rewards viz. persuasion, emotion, Politeness-Strategy Consistency, Dialogue-Coherence and Non-repetitiveness. |
| Outcome: | The proposed system increases the rate of persuasive responses with emotion and politeness acknowledgement compared to the current state-of-the-art dialogue models while maintaining the linguistic quality. |
Correcting Language Model Outputs by Editing Salient Layers (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing models that use manual layer selection require prior domain knowledge and expensive empirical layer selection methods. |
| Approach: | They propose a model editing approach that selectively edits a small subset of model parameters to update the factual knowledge. |
| Outcome: | The proposed solution matches the accuracy of previous approaches with only 1/3 of their edits, enabling efficient updates to the parametric knowledge in large language models. |
MedEx: Enhancing Medical Question-Answering with First-Order Logic based Reasoning and Knowledge Injection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing knowledge triples are ineffective in medical question-answering because of superfluous data and inability to capture complex relationships between symptoms and treatments. |
| Approach: | They propose a first-order logical reasoning model that uses First-Order Logic to model intricate relationships between diseases and treatments. |
| Outcome: | The proposed model captures the interplay of symptoms, diseases, and treatments, enhancing context comprehension. |
Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing models for persuasive dialogue lack emotion annotated data, so we use transformers to provide emotion based feedbacks to our RL agent. |
| Approach: | They propose to use a language model to generate empathetic persuasive dialogues . they annotate existing data with emotions and build transformers to provide feedbacks based on emotion. |
| Outcome: | The proposed model increases the rate of generating persuasive responses compared to state-of-the-art models while maintaining the language quality. |