Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and complex objectives, making models vulnerable to generating harmful content. We propose Safety Arithmetic, a training-free framework enhancing LLM safety across different scenarios: Base models, Supervised fine-tuned models (SFT), and Edited models. Safety Arithmetic involves Harm Direction Removal to avoid harmful content and Safety Alignment to promote safe responses. Additionally, we present NoIntentEdit, a dataset highlighting edit instances that could compromise model safety if used unintentionally. Our experiments show that Safety Arithmetic significantly improves safety measures, reduces over-safety, and maintains model utility, outperforming existing methods in ensuring safe content generation.

This paper introduces a novel framework that combines graph-driven context retrieval in conjunction to knowledge graphs based enhancement, honing the proficiency of LLMs, especially in domain specific community question answering platforms like AskUbuntu, Unix, and ServerFault. We conduct experiments on various LLMs with different parameter sizes to evaluate their ability to ground knowledge and determine factual accuracy in answers to open-ended questions. Our methodology GraphContextGen consistently outperforms dominant text-based retrieval systems, demonstrating its robustness and adaptability to a larger number of use cases. This advancement highlights the importance of pairing context rich data retrieval with LLMs, offering a renewed approach to knowledge sourcing and generation in AI systems. We also show that, due to rich contextual data retrieval, the crucial entities, along with the generated answer, remain factually coherent with the gold answer. We shall release the source code and datasets upon acceptance.

In the rapidly advancing field of artificial intelligence, the concept of ‘Red-Teaming’ or ‘Jailbreaking’ large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking paradox: while injecting accurate information is crucial for model reliability, it can paradoxically destabilize the model’s foundational framework, resulting in unpredictable and potentially unsafe behaviors. Additionally, we propose a benchmark dataset NicheHazardQA to investigate this unsafe behavior both within the same and cross topical domain. This aspect of our research sheds light on how the edits, impact the model’s safety metrics and guardrails. Our findings show that model editing serves as a cost-effective tool for topical red-teaming by methodically applying targeted edits and evaluating the resultant model behavior.

Recently, influence functions present an apparatus for achieving explainability for deep neural models by quantifying the perturbation of individual train instances that might impact a test prediction. Our objectives in this paper are twofold. First we incorporate influence functions as a feedback into the model to improve its performance. Second, in a dataset extension exercise, using influence functions to automatically identify data points that have been initially ‘silver’ annotated by some existing method and need to be cross-checked (and corrected) by annotators to improve the model performance. To meet these objectives, in this paper, we introduce InfFeed, which uses influence functions to compute the influential instances for a target instance. Toward the first objective, we adjust the label of the target instance based on its influencer(s) label. In doing this, InfFeed outperforms the state-of-the-art baselines (including LLMs) by a maximum macro F1-score margin of almost 4% for hate speech classification, 3.5% for stance classification, and 3% for irony and 2% for sarcasm detection. Toward the second objective we show that manually re-annotating only those silver annotated data points in the extension set that have a negative influence can immensely improve the model performance bringing it very close to the scenario where all the data points in the extension set have gold labels. This allows for huge reduction of the number of data points that need to be manually annotated since out of the silver annotated extension dataset, the influence function scheme picks up ~1/1000 points that need manual correction.

Social media often serves as a breeding ground for various hateful and offensive content. Identifying such content on social media is crucial due to its impact on the race, gender, or religion in an unprejudiced society. However, while there is extensive research in hate speech detection in English, there is a gap in hateful content detection in low-resource languages like Bengali. Besides, a current trend on social media is the use of Romanized Bengali for regular interactions. To overcome the existing research’s limitations, in this study, we develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets. We implement several baseline models for the classification of such hateful posts. We further explore the interlingual transfer mechanism to boost classification performance. Finally, we perform an in-depth error analysis by looking into the misclassified posts by the models. While training actual and Romanized datasets separately, we observe that XLM-Roberta performs the best. Further, we witness that on joint training and few-shot training, MuRIL outperforms other models by interpreting the semantic expressions better. We make our code and dataset public for others.

Social media platforms often act as breeding grounds for various forms of trolling or malicious content targeting users or communities. One way of trolling users is by creating memes, which in most cases unites an image with a short piece of text embedded on top of it. The situation is more complex for multilingual(e.g., Tamil) memes due to the lack of benchmark datasets and models. We explore several models to detect Troll memes in Tamil based on the shared task, “Troll Meme Classification in DravidianLangTech2022” at ACL-2022. We observe while the text-based model MURIL performs better for Non-troll meme classification, the image-based model VGG16 performs better for Troll-meme classification. Further fusing these two modalities help us achieve stable outcomes in both classes. Our fusion model achieved a 0.561 weighted average F1 score and ranked second in this task.

With the advent of contextualized embeddings, attention towards neural ranking approaches for Information Retrieval increased considerably. However, two aspects have remained largely neglected: i) queries usually consist of few keywords only, which increases ambiguity and makes their contextualization harder, and ii) performing neural ranking on non-English documents is still cumbersome due to shortage of labeled datasets. In this paper we present SIR (Sense-enhanced Information Retrieval) to mitigate both problems by leveraging word sense information. At the core of our approach lies a novel multilingual query expansion mechanism based on Word Sense Disambiguation that provides sense definitions as additional semantic information for the query. Importantly, we use senses as a bridge across languages, thus allowing our model to perform considerably better than its supervised and unsupervised alternatives across French, German, Italian and Spanish languages on several CLEF benchmarks, while being trained on English Robust04 data only. We release SIR at https://github.com/SapienzaNLP/sir.

This paper describes the participation of LIMSI_UPV team in SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text. The proposed approach competed in SentiMix HindiEnglish subtask, that addresses the problem of predicting the sentiment of a given Hindi-English code-mixed tweet. We propose Recurrent Convolutional Neural Network that combines both the recurrent neural network and the convolutional network to better capture the semantics of the text, for code-mixed sentiment analysis. The proposed system obtained 0.69 (best run) in terms of F1 score on the given test data and achieved the 9th place (Codalab username: somban) in the SentiMix Hindi-English subtask.

This paper describes our system submissions as part of our participation (team name: JU_ETCE_17_21) in the SemEval 2019 shared task 6: “OffensEval: Identifying and Catego- rizing Offensive Language in Social Media”. We participated in all the three sub-tasks: i) Sub-task A: offensive language identification, ii) Sub-task B: automatic categorization of of- fense types, and iii) Sub-task C: offense target identification. We employed machine learn- ing as well as deep learning approaches for the sub-tasks. We employed Convolutional Neural Network (CNN) and Recursive Neu- ral Network (RNN) Long Short-Term Memory (LSTM) with pre-trained word embeddings. We used both word2vec and Glove pre-trained word embeddings. We obtained the best F1- score using CNN based model for sub-task A, LSTM based model for sub-task B and Lo- gistic Regression based model for sub-task C. Our best submissions achieved 0.7844, 0.5459 and 0.48 F1-scores for sub-task A, sub-task B and sub-task C respectively.

In this paper, we describe a deep learning framework for analyzing the customer feedback as part of our participation in the shared task on Customer Feedback Analysis at the 8th International Joint Conference on Natural Language Processing (IJCNLP 2017). A Convolutional Neural Network (CNN) based deep neural network model was employed for the customer feedback task. The proposed system was evaluated on two languages, namely, English and French.