The carbon footprint of any deployed Large Language Model (LLM) accumulates during inference, where repeated use of the model substantially exceeds the one-time cost of fine-tuning. Yet most efficiency interventions target either pre-training scale or post-hoc compression. We ask whether folding a calibrated, differentiable energy surrogate into the fine-tuning objective can produce inference behavior that gains task accuracy at zero or near-zero carbon cost, a break-even configuration. We propose a joint loss mechanism with a per-model carbon-emission parameter, a linear surrogate over parameter norm, FLOP proxy, and a memory proxy, fit from on-hardware energy profiling. We fine-tune three architecturally distinct families: Gemma-2 2B, Llama-3.1 8B, and Qwen-2.5 14B, and evaluate inference F1 and CO$_2$ emissions on three MMLU subjects: abstract algebra, philosophy, and formal logic. We discover from several outcomes that the carbon term behaves as either harmful interference or beneficial regularization depending on the task structure. We position calibrated carbon-aware fine-tuning as a lightweight, drop-in regularizer with a non-empty but model and task-dependent break-even region. This is an ongoing work, and we will release our codebase soon.
This comprehensive study introduces an advanced
A
rtificial Intelligence for
I
ndian
L
egal
Q
uestion
A
nswering or system tailored for the Indian legal context. leverages a variety of embedding and generative models, including the latest Large Language Models (LLMs), to address the unique challenges posed by the intricate and diverse nature of Indian legal texts, to enhance the accuracy and reliability of legal question responses. We conducted rigorous evaluations using both lexical and semantic metrics that are enriched by expert legal feedback to ensure relevance and accuracy. Our findings underscore the effectiveness of the Retrieval-Augmented Generation (RAG) paradigm in improving answer quality, particularly in complex legal domains. Additionally, we explored the performance on standardized tests such as the All India Bar Exam (AIBE), thus providing a robust benchmark for a practical application. Under the study’s evaluation protocol, some AI-generated responses received higher ratings than the available reference answers, particularly when they contained accurate and relevant supporting detail. This finding is specific to the evaluated dataset and rating criteria and should not be interpreted as evidence that the models generally outperform qualified legal professionals. We also discuss the challenges encountered, such as the need for precise context and the risks of model hallucination, and propose directions for future research to further refine AI capabilities in the legal field. This study aims to pave the way for enhanced legal decision-making support systems, making them more accessible and effective for legal professionals and the public alike.
S. Nigam, Shubham Kumar Mishra, Noel Shallum et al.· Artificial Intelligence and...· 1 citation
This work presents PROSLEX (PRediction Of Statutes and LEgal eXplanation), a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context, positioning PROSLEX as a benchmark for developing explainable AI systems that can support legal practitioners while advancing research in interpretable legal NLP.
Subinay Adhikary, Upal Bhattacharya, Vivek K. Singh et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
