Explore the vast range of titles available.

Enhancers are distal cis-regulatory elements that dictate complex transcriptional repertoire. Herpes viruses exhibit programmed latent and lytic gene expression depending on the infected tissue and physiological state. Previously, using a systematic functional assay, we identified six enhancers within the genome of Kaposi’s sarcoma-associated herpesvirus (KSHV). In this study, we present a natural language processing model (NLP)-based tool, ENHAvir, that is trained with these six enhancers and non-enhancer control sequences from the KSHV genome. ENHAvir identifies known enhancers and predicted novel enhancer elements in human herpesviruses. The activity of the predicted enhancers in HSV-2, HCMV, HHV-6, HHV-7, and EBV is confirmed in an enhancer reporter assay. The terminal repeats of all the herpes viruses also serve as a strong enhancer. Comparing herpesvirus enhancers with human enhancers reveals conserved enhancer signatures and the involvement of Alu elements. Here, we present an AI tool that successfully predicts enhancers in both viral and human genomes. Artificial intelligence (AI) can detect and predict patterns that are hidden from the human eye and from conventional homology-detection tools. Enhancers are distal DNA cis-regulatory elements that regulate complex transcriptional repertoire. A natural language processing (NLP) model was trained using only six enhancer sequences from the Kaposi’s sarcoma-associated herpesvirus (KSHV) genome. This tool, termed ENHAvir, can identify known enhancers and predict novel enhancer elements in other herpesviruses, different viruses, and the human genome. The activity of the predicted enhancers in HSV-2, HCMV, HHV-6, HHV-7, and EBV was confirmed experimentally, enabling the creation of a comprehensive enhancer map of human herpesviruses. All human herpesviruses contain terminal repeats (TRs), which play important roles in cleaving the viral genome into genome-size units, genome encapsidation, and genome circularization following entry into the nucleus of a newly infected cell. This study adds another role for the TR of all human herpesviruses, a strong enhancer with the features of a “viral super enhancer”. Comparing herpesvirus enhancers with human enhancers revealed conserved enhancer signatures and the involvement of Alu elements. Here, an AI tool is presented that successfully predicts enhancers in both viral and human genomes.

We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong transformer-based baselines. The dataset is available at https://github.com/declare-lab/RECCON . Recognizing the cause behind emotions in text is a fundamental yet under-explored area of research in NLP. Advances in this area hold the potential to improve interpretability and performance in affect-based models. Identifying emotion causes at the utterance level in conversations is particularly challenging due to the intermingling dynamics among the interlocutors. We introduce the task of Recognizing Emotion Cause in CONversations with an accompanying dataset named RECCON, containing over 1,000 dialogues and 10,000 utterance cause/effect pairs. Furthermore, we define different cause types based on the source of the causes, and establish strong Transformer-based baselines to address two different sub-tasks on this dataset. Our transformer-based baselines, which leverage contextual pre-trained embeddings, such as RoBERTa, outperform the state-of-the-art emotion cause extraction approaches on our dataset. We introduce a new task highly relevant for (explainable) emotion-aware artificial intelligence: recognizing emotion cause in conversations, provide a new highly challenging publicly available dialogue-level dataset for this task, and give strong baseline results on this dataset.

Zero-shot learning — the problem of training and testing on a completely disjoint set of classes — relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of human-defined attributes or distributed word embeddings are used to facilitate this transfer by improving the association between visual and semantic embeddings. In this paper, we take advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder. Our experiments performed on three standard benchmark datasets surpass the strong baselines when we fuse our commonsense embeddings with existing semantic embeddings, i.e., human-defined attributes and distributed word embeddings. This work paves the path to more brain-inspired approaches to zero-short learning.

Logical reasoning is a key task for artificial intelligence due to it's role in major downstream tasks such as Question Answering, Summarization. Recent methods in improving the reasoning ability of LLMs fall short in correctly converting a natural language reasoning problem to an equivalent logical formulation, which hinders the framework's overall ability to reason. Towards this, we propose to use finetuning on a preference optimization dataset to learn to parse and represent a natural language problem as a whole to a consistent logical program by 1) introducing a new supervised and preference optimization dataset LogicPO, and 2) adopting popular techniques such as Direct Preference Optimization (DPO), Kahneman-Tversky optimization (KTO) to finetune open-source LLMs. Our best model with Phi-3.5 consistently outperforms GPT-3.5-turbo's (8-shot) by producing 10% more logically correct and with 14% less syntax errors. Through the framework and our improved evaluation metrics, we offer a promising direction in improving the logical reasoning of LLMs by better representing them in their logical formulations.

Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question. Small vision-language models (sVLMs) such as ViLT, VisualBERT and FLAVA therefore lag behind their larger generative counterparts. To study the effect of careful commonsense knowledge integration on sVLMs, we present an end-to-end framework (NLKI) that (i) retrieves natural language facts, (ii) prompts an LLM to craft natural language explanations, and (iii) feeds both signals to sVLMs respectively across two commonsense VQA datasets (CRIC, AOKVQA) and a visual-entailment dataset (e-SNLI-VE). Facts retrieved using a fine-tuned ColBERTv2 and an object information-enriched prompt yield explanations that largely cut down hallucinations, while lifting the end-to-end answer accuracy by up to 7% (across 3 datasets), making FLAVA and other models in NLKI match or exceed medium-sized VLMs such as Qwen-2 VL-2B and SmolVLM-2.5B. As these benchmarks contain 10-25% label noise, additional finetuning using noise-robust losses (such as symmetric cross entropy and generalised cross entropy) adds another 2.5% in CRIC, and 5.5% in AOKVQA. Our findings expose when LLM-based commonsense knowledge beats retrieval from commonsense knowledge bases, how noise-aware training stabilises small models in the context of external knowledge augmentation, and why parameter-efficient commonsense reasoning is now within reach for 250M models.

The task of table summarization involves generating text that both succinctly and accurately represents the table or a specific set of highlighted cells within a table. While significant progress has been made in table to text generation techniques, models still mostly generate descriptive summaries, which reiterates the information contained within the table in sentences. Through analysis of popular table to text benchmarks (ToTTo (Parikh et al., 2020 and InfoTabs (Gupta et al., 2020) we observe that in order to generate the ideal summary, multiple types of reasoning is needed coupled with access to knowledge beyond the scope of the table. To address this gap, we propose ReTAG, a table and reasoning aware model that uses vector-quantization to infuse different types of analytical reasoning into the output. ReTAG achieves 2.2%, 2.9% improvement on the PARENT metric in the relevant slice of ToTTo and InfoTabs for the table to text generation task over state of the art baselines. Through human evaluation, we observe that output from ReTAG is upto 12% more faithful and analytical compared to a strong table-aware model. To the best of our knowledge, ReTAG is the first model that can controllably use multiple reasoning methods within a structure-aware sequence to sequence model to surpass state of the art performance in multiple table to text tasks. We extend (and open source 35.6K analytical, 55.9k descriptive instances) the ToTTo, InfoTabs datasets with the reasoning categories used in each reference sentences.

The Natural Language Inference (NLI) task often requires reasoning over multiple steps to reach the conclusion. While the necessity of generating such intermediate steps (instead of a summary explanation) has gained popular support, it is unclear how to generate such steps without complete end-to-end supervision and how such generated steps can be further utilized. In this work, we train a sequence-to-sequence model to generate only the next step given an NLI premise and hypothesis pair (and previous steps); then enhance it with external knowledge and symbolic search to generate intermediate steps with only next-step supervision. We show the correctness of such generated steps through automated and human verification. Furthermore, we show that such generated steps can help improve end-to-end NLI task performance using simple data augmentation strategies, across multiple public NLI datasets.

Visual interest & affect prediction is a very interesting area of research in the area of computer vision. In this paper, we propose a transfer learning and attention mechanism based neural network model to predict visual interest & affective dimensions in digital photos. Learning the multi-dimensional affects is addressed through a multi-task learning framework. With various experiments we show the effectiveness of the proposed approach. Evaluation of our model on the benchmark dataset shows large improvement over current state-of-the-art systems.

The releases of OpenAI's o-[n] series, such as o1, o3, and o4-mini, mark a significant paradigm shift in Large Language Models towards advanced reasoning capabilities. Notably, models like o3 have demonstrated strong performance on benchmarks like the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI). However, this benchmark is limited to symbolic patterns, whereas humans often perceive and reason about multimodal scenarios involving both vision and language data. Thus, there is an urgent need to investigate advanced reasoning capabilities in multimodal tasks. To this end, we track the evolution of the GPT-[n] and o-[n] series models (including o1, o3, and o4-mini) on challenging multimodal puzzles from PuzzleVQA and AlgoPuzzleVQA, which demand fine-grained visual perception. Our results reveal that o-[n] series, particularly later iterations like o3 and o4-mini, significantly outperform the GPT-[n] series and show strong scalability in multimodal reasoning. Nonetheless, despite these substantial advancements and the superior capabilities demonstrated by the o-[n] series, our findings highlight that even these leading models face persistent challenges. Difficulties are particularly evident in tasks requiring precise visual perception, robust compositional reasoning across multiple visual attributes, and solving complex algorithmic or highly combinatorial puzzles, indicating critical areas for future AGI development. We plan to continuously track new models in the series and update our results in this paper accordingly. All resources used in this evaluation are openly available at https://github.com/declare-lab/LLM-PuzzleTest.

Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or decoder-only architecture. Interestingly, despite being introduced four years ago, T5-based LLMs, such as FLAN-T5, continue to outperform the latest decoder-based LLMs, such as LLAMA and VICUNA, on tasks that require general problem-solving skills. This performance discrepancy can be attributed to three key factors: (1) Pre-training data, (2) Backbone architecture, and (3) Instruction dataset. In this technical report, our main focus is on investigating the impact of the third factor by leveraging VICUNA, a large language model based on LLAMA, which has undergone fine-tuning on ChatGPT conversations. To achieve this objective, we fine-tuned VICUNA using a customized instruction dataset collection called FLANMINI. This collection includes a subset of the large-scale instruction dataset known as FLAN, as well as various code-related datasets and conversational datasets derived from ChatGPT/GPT-4. This dataset comprises a large number of tasks that demand problem-solving skills. Our experimental findings strongly indicate that the enhanced problem-solving abilities of our model, FLACUNA, are obtained through fine-tuning VICUNA on the FLAN dataset, leading to significant improvements across numerous benchmark datasets in INSTRUCTEVAL. FLACUNA is publicly available at https://huggingface.co/declare-lab/flacuna-13b-v1.0.