Cover Image

Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Das, Kunal Kingkar, Jagadeeshan, Manoj Balaji, Sahith, Nallani Chakravartula, Sandhan, Jivnesh, Goyal, Pawan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PINGALA: Prosody-Aware Decoding for Sanskrit Poetry Generation
by: Jagadeeshan, Manoj Balaji, et al.
Published: (2026)

Mahānāma: A Unique Testbed for Literary Entity Discovery and Linking
by: Sarkar, Sujoy, et al.
Published: (2025)

Mitrasamgraha: A Comprehensive Classical Sanskrit Machine Translation Dataset
by: Nehrdich, Sebastian, et al.
Published: (2026)

Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents
by: Jagadeeshan, Manoj Balaji, et al.
Published: (2025)

CSSL: Contrastive Self-Supervised Learning for Dependency Parsing on Relatively Free Word Ordered and Morphologically Rich Low Resource Languages
by: Ray, Pretam, et al.
Published: (2024)

Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry
by: Kumar, Sujeet, et al.
Published: (2025)

CAPE: Context-Aware Personality Evaluation Framework for Large Language Models
by: Sandhan, Jivnesh, et al.
Published: (2025)

Persona Jailbreaking in Large Language Models
by: Sandhan, Jivnesh, et al.
Published: (2026)

Can We Trust LLM Detectors?
by: Sandhan, Jivnesh, et al.
Published: (2026)

Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs
by: Jagadeeshan, Manoj Balaji, et al.
Published: (2025)

Can LLMs Generate High-Quality Task-Specific Conversations?
by: Li, Shengqi, et al.
Published: (2025)

Bidirectional Awareness Induction in Autoregressive Seq2Seq Models
by: Hu, Jia Cheng, et al.
Published: (2024)

UniGenCoder: Merging Seq2Seq and Seq2Tree Paradigms for Unified Code Generation
by: Shao, Liangying, et al.
Published: (2025)

How Robust are the Tabular QA Models for Scientific Tables? A Study using Customized Dataset
by: Ghosh, Akash, et al.
Published: (2024)

Seq vs Seq: An Open Suite of Paired Encoders and Decoders
by: Weller, Orion, et al.
Published: (2025)

Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning
by: Khodabandeh, Mahdi, et al.
Published: (2026)

American Sign Language to Text Translation using Transformer and Seq2Seq with LSTM
by: Putra, Gregorius Guntur Sunardi, et al.
Published: (2024)

Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
by: Lee, Jihyeon, et al.
Published: (2023)

Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
by: Atil, Berk, et al.
Published: (2025)

Improving Bangla Linguistics: Advanced LSTM, Bi-LSTM, and Seq2Seq Models for Translating Sylheti to Modern Bangla
by: Das, Sourav Kumar, et al.
Published: (2025)

SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation
by: Lindemann, Matthias, et al.
Published: (2023)

Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5
by: Sun, Huey, et al.
Published: (2025)

Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
by: Phuc, Luu Huu, et al.
Published: (2026)

Seq2Seq Model-Based Chatbot with LSTM and Attention Mechanism for Enhanced User Interaction
by: Benaddi, Lamya, et al.
Published: (2024)

Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective
by: Garcia-Estrada, Ernesto, et al.
Published: (2026)

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
by: Yang, Yan, et al.
Published: (2024)

The Poetry and Prose of Wang Wei
by: Rouzer, Paul
Published: (2021)

The Poetry and Prose of Wang Wei
by: Rouzer, Paul
Published: (2021)

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
by: Sun, Jie, et al.
Published: (2026)

Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
by: De Mel, Yomal, et al.
Published: (2024)

Frontier LLMs Still Struggle with Simple Reasoning Tasks
by: Malek, Alan, et al.
Published: (2025)

Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation
by: Gao, Ge, et al.
Published: (2024)

Learning Transductions and Alignments with RNN Seq2seq Models
by: Wang, Zhengxiang
Published: (2023)

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
by: Cao, Jinghan, et al.
Published: (2026)

SeqPE: Transformer with Sequential Position Encoding
by: Li, Huayang, et al.
Published: (2025)

Efficient Seq2seq Coreference Resolution Using Entity Representations
by: Grenander, Matt, et al.
Published: (2025)

OptiSeq: Ordering Examples On-The-Fly for In-Context Learning
by: Bhope, Rahul Atul, et al.
Published: (2025)

It Helps to Take a Second Opinion: Teaching Smaller LLMs to Deliberate Mutually via Selective Rationale Optimisation
by: Patnaik, Sohan, et al.
Published: (2025)

ReaSeq: Unleashing World Knowledge via Reasoning for Sequential Modeling
by: Tang, Jiakai, et al.
Published: (2025)

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
by: Arefin, Md Rifat, et al.
Published: (2024)