LLMs are increasingly used as seq2seq translators from natural language utterances to structured programs, a process called semantic interpretation. Unlike atomic labels or token sequences, programs are naturally represented as abstract syntax trees (ASTs). Such structured representation raises novel issues related to the design and selection of in-context examples (ICEs) presented to the LLM. We focus on decomposing the pool of available ICE trees into fragments, some of which may be better suited to solving the test instance. Next, we propose how to use (additional invocations of) an LLM with prompted syntax constraints to automatically map the fragments to corresponding utterances. Finally, we adapt and extend a recent method for diverse ICE selection to work with whole and fragmented ICE instances. We evaluate our system, SCUD4ICL, on popular diverse semantic parsing benchmarks, showing visible accuracy gains from our proposed decomposed diverse demonstration method. Benefits are particularly notable for smaller LLMs, ICE pools having larger labeled trees, and programs in lower resource languages.

Reasoning and linguistic skills form the cornerstone of human intelligence, facilitating problem-solving and decision-making. Recent advances in Large Language Models (LLMs) have led to impressive linguistic capabilities and emergent reasoning behaviors, fueling widespread adoption across application domains. However, LLMs still struggle with complex reasoning tasks, highlighting their systemic limitations. In this work, we focus on evaluating whether LLMs have the requisite representations to reason using two foundational relationships: “equivalence” and “inheritance”. We introduce novel tasks and benchmarks spanning six languages and observe that current SOTA LLMs often produce conflicting answers to the same questions across languages in 17.3-57.5% of cases and violate inheritance constraints in up to 37.2% cases. To enhance consistency across languages, we propose novel “Compositional Representations” where tokens are represented as composition of equivalent tokens across languages, with resulting conflict reduction (up to -4.7%) indicating benefits of shared LLM representations.

Intent detection is a critical component of task-oriented dialogue systems (TODS) which enables the identification of suitable actions to address user utterances at each dialog turn. Traditional approaches relied on computationally efficient supervised sentence transformer encoder models, which require substantial training data and struggle with out-of-scope (OOS) detection. The emergence of generative large language models (LLMs) with intrinsic world knowledge presents new opportunities to address these challenges.In this work, we adapt SOTA LLMs using adaptive in-context learning and chain-of-thought prompting for intent detection, and compare their performance with contrastively fine-tuned sentence transformer (SetFit) models to highlight prediction quality and latency tradeoff. We propose a hybrid system using uncertainty based routing strategy to combine the two approaches that along with negative data augmentation results in achieving the best of both worlds ( i.e. within 2% of native LLM accuracy with 50% less latency). To better understand LLM OOS detection capabilities, we perform controlled experiments revealing that this capability is significantly influenced by the scope of intent labels and the size of the label space. We also introduce a two-step approach utilizing internal LLM representations, demonstrating empirical gains in OOS detection accuracy and F1-score by >5% for the Mistral-7B model.

Code-mixing is ubiquitous in multilingual societies, which makes it vital to build models for code-mixed data to power human language interfaces. Existing multilingual transformer models trained on pure corpora lack the ability to intermix words of one language into the structure of another. These models are also not robust to orthographic variations. We propose CoMixCoMix is not a trademark and only used to refer to our models for code-mixed data for presentational brevity., a pretraining approach to improve representation of code-mixed data in transformer models by incorporating phonetic signals, a modified attention mechanism, and weak supervision guided generation by parts-of-speech constraints. We show that CoMix improves performance across four code-mixed tasks: machine translation, sequence classification, named entity recognition (NER), and abstractive summarization. It also achieves the new SOTA performance for English-Hinglish translation and NER on LINCE Leaderboard and provides better generalization on out-of-domain translation. Motivated by variations in human annotations, we also propose a new family of metrics based on phonetics and demonstrate that the phonetic variant of BLEU correlates better with human judgement than BLEU on code-mixed text.

We describe our system that ranked first in Hope Speech Detection (HSD) shared task and fourth in Offensive Language Identification (OLI) shared task, both in Tamil language. The goal of HSD and OLI is to identify if a code-mixed comment or post contains hope speech or offensive content respectively. We pre-train a transformer-based model RoBERTa using synthetically generated code-mixed data and use it in an ensemble along with their pre-trained ULMFiT model available from iNLTK.

Intent Detection systems in the real world are exposed to complexities of imbalanced datasets containing varying perception of intent, unintended correlations and domain-specific aberrations. To facilitate benchmarking which can reflect near real-world scenarios, we introduce 3 new datasets created from live chatbots in diverse domains. Unlike most existing datasets that are crowdsourced, our datasets contain real user queries received by the chatbots and facilitates penalising unwanted correlations grasped during the training process. We evaluate 4 NLU platforms and a BERT based classifier and find that performance saturates at inadequate levels on test sets because all systems latch on to unintended patterns in training data.

We present iNLTK, an open-source NLP library consisting of pre-trained language models and out-of-the-box support for Data Augmentation, Textual Similarity, Sentence Embeddings, Word Embeddings, Tokenization and Text Generation in 13 Indic Languages. By using pre-trained models from iNLTK for text classification on publicly available datasets, we significantly outperform previously reported results. On these datasets, we also show that by using pre-trained models and data augmentation from iNLTK, we can achieve more than 95% of the previous best performance by using less than 10% of the training data. iNLTK is already being widely used by the community and has 40,000+ downloads, 600+ stars and 100+ forks on GitHub. The library is available at https://github.com/goru001/inltk.

Catastrophic forgetting — whereby a model trained on one task is fine-tuned on a second, and in doing so, suffers a “catastrophic” drop in performance over the first task — is a hurdle in the development of better transfer learning techniques. Despite impressive progress in reducing catastrophic forgetting, we have limited understanding of how different architectures and hyper-parameters affect forgetting in a network. With this study, we aim to understand factors which cause forgetting during sequential training. Our primary finding is that CNNs forget less than LSTMs. We show that max-pooling is the underlying operation which helps CNNs alleviate forgetting compared to LSTMs. We also found that curriculum learning, placing a hard task towards the end of task sequence, reduces forgetting. We analysed the effect of fine-tuning contextual embeddings on catastrophic forgetting and found that using embeddings as feature extractor is preferable to fine-tuning in continual learning setup.