Recent LLM (Large Language Models) advancements benefit many fields such as education and finance, but HR has hundreds of repetitive processes, such as access requests, medical claim filing and time-off submissions, which are unaddressed. We relate these tasks to the LLM agent, which has addressed tasks such as writing assisting and customer support. We present HR-Agent, an efficient, confidential, and HR-specific LLM-based task-oriented dialogue system tailored for automating repetitive HR processes such as medical claims and access requests. Since conversation data is not sent to an LLM during inference, it preserves confidentiality required in HR-related tasks.

Large language models (LLMs) require alignment, such as instruction-tuning or reinforcement learning from human feedback, to effectively and safely follow user instructions. This process necessitates training aligned versions for every model size in each model family, resulting in significant computational overhead. In this work, we propose nudging, a simple, plug-and-play, and training-free algorithm that aligns any base model at inference time using a small aligned model. Nudging is motivated by recent findings that alignment primarily alters the model's behavior on a small subset of stylistic tokens, such as "Sure" or "Thank". We find that base models are significantly more uncertain when generating these tokens. Leveraging this observation, nudging employs a small aligned model to generate nudging tokens to steer the large base model's output toward desired directions when the base model's uncertainty is high. We evaluate the effectiveness of nudging across 3 model families and 13 tasks, covering reasoning, general knowledge, instruction following, and safety benchmarks. Without any additional training, nudging a large base model with a 7x - 14x smaller aligned model achieves zero-shot performance comparable to, and sometimes surpassing, that of large aligned models. For example, nudging OLMo-7b with OLMo-1b-instruct, affecting less than 9% of tokens, achieves a 10% absolute improvement on GSM8K over OLMo-7b-instruct. Unlike prior inference-time tuning methods, nudging enables off-the-shelf collaboration between model families. For instance, nudging Gemma-2-27b with Llama-2-7b-chat outperforms Llama-2-70b-chat on various tasks. Overall, this work introduces a simple yet powerful approach to token-level model collaboration, offering a modular solution to LLM alignment. Our project website: https://fywalter.github.io/nudging/ .

We introduce JurEE, an ensemble of efficient, encoder-only transformer models designed to strengthen safeguards in AI-User interactions within LLM-based systems. Unlike existing LLM-as-Judge methods, which often struggle with generalization across risk taxonomies and only provide textual outputs, JurEE offers probabilistic risk estimates across a wide range of prevalent risks. Our approach leverages diverse data sources and employs progressive synthetic data generation techniques, including LLM-assisted augmentation, to enhance model robustness and performance. We create an in-house benchmark comprising of other reputable benchmarks such as the OpenAI Moderation Dataset and ToxicChat, where we find JurEE significantly outperforms baseline models, demonstrating superior accuracy, speed, and cost-efficiency. This makes it particularly suitable for applications requiring stringent content moderation, such as customer-facing chatbots. The encoder-ensemble's modular design allows users to set tailored risk thresholds, enhancing its versatility across various safety-related applications. JurEE's collective decision-making process, where each specialized encoder model contributes to the final output, not only improves predictive accuracy but also enhances interpretability. This approach provides a more efficient, performant, and economical alternative to traditional LLMs for large-scale implementations requiring robust content moderation.

Large Language Models (LLMs), such as GPT-4 and BERT, have rapidly gained traction in natural language processing (NLP) and are now integral to financial decision-making. However, their deployment introduces critical challenges, particularly in perpetuating gender biases that can distort decision-making outcomes in high-stakes economic environments. This paper investigates gender bias in LLMs through both mathematical proofs and empirical experiments using the Word Embedding Association Test (WEAT), demonstrating that LLMs inherently reinforce gender stereotypes even without explicit gender markers. By comparing the decision-making processes of humans and LLMs, we reveal fundamental differences: while humans can override biases through ethical reasoning and individualized understanding, LLMs maintain bias as a rational outcome of their mathematical optimization on biased data. Our analysis proves that bias in LLMs is not an unintended flaw but a systematic result of their rational processing, which tends to preserve and amplify existing societal biases encoded in training data. Drawing on existentialist theory, we argue that LLM-generated bias reflects entrenched societal structures and highlights the limitations of purely technical debiasing methods. This research underscores the need for new theoretical frameworks and interdisciplinary methodologies that address the ethical implications of integrating LLMs into economic and financial decision-making. We advocate for a reconceptualization of how LLMs influence economic decisions, emphasizing the importance of incorporating human-like ethical considerations into AI governance to ensure fairness and equity in AI-driven financial systems.

Large language models (LLMs) hold great potential to improve access to justice. However, a major challenge in applying AI and LLMs in legal contexts, where consistency and reliability are crucial, is the need for System 2 reasoning. In this paper, we explore the integration of LLMs with logic programming to enhance their ability to reason, bringing their strategic capabilities closer to that of a skilled lawyer. Our objective is to translate laws and contracts into logic programs that can be applied to specific legal cases, with a focus on insurance contracts. We demonstrate that while GPT-4o fails to encode a simple health insurance contract into logical code, the recently released OpenAI o1-preview model succeeds, exemplifying how LLMs with advanced System 2 reasoning capabilities can expand access to justice.

Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives. To address these limitations, we propose RMB, a comprehensive RM benchmark that covers over 49 real-world scenarios and includes both pairwise and Best-of-N (BoN) evaluations to better reflect the effectiveness of RMs in guiding alignment optimization. We demonstrate a positive correlation between our benchmark and the downstream alignment task performance. Based on our benchmark, we conduct extensive analysis on the state-of-the-art RMs, revealing their generalization defects that were not discovered by previous benchmarks, and highlighting the potential of generative RMs. Furthermore, we delve into open questions in reward models, specifically examining the effectiveness of majority voting for the evaluation of reward models and analyzing the impact factors of generative RMs, including the influence of evaluation criteria and instructing methods. Our evaluation code and datasets are available at https://github.com/Zhou-Zoey/RMB-Reward-Model-Benchmark.

Kenya, known for its linguistic diversity, faces unique challenges and promising opportunities in advancing Natural Language Processing (NLP) technologies, particularly for its underrepresented indigenous languages. This survey provides a detailed assessment of the current state of NLP in Kenya, emphasizing ongoing efforts in dataset creation, machine translation, sentiment analysis, and speech recognition for local dialects such as Kiswahili, Dholuo, Kikuyu, and Luhya. Despite these advancements, the development of NLP in Kenya remains constrained by limited resources and tools, resulting in the underrepresentation of most indigenous languages in digital spaces. This paper uncovers significant gaps by critically evaluating the available datasets and existing NLP models, most notably the need for large-scale language models and the insufficient digital representation of Indigenous languages. We also analyze key NLP applications: machine translation, information retrieval, and sentiment analysis-examining how they are tailored to address local linguistic needs. Furthermore, the paper explores the governance, policies, and regulations shaping the future of AI and NLP in Kenya and proposes a strategic roadmap to guide future research and development efforts. Our goal is to provide a foundation for accelerating the growth of NLP technologies that meet Kenya's diverse linguistic demands.

Privacy regulations like the GDPR in Europe and the CCPA in the US allow users the right to remove their data ML applications. Machine unlearning addresses this by modifying the ML parameters in order to forget the influence of a specific data point on its weights. Recent literature has highlighted that the contribution from data point(s) can be forged with some other data points in the dataset with probability close to one. This allows a server to falsely claim unlearning without actually modifying the model's parameters. However, in distributed paradigms such as FL, where the server lacks access to the dataset and the number of clients are limited, claiming unlearning in such cases becomes a challenge. This paper introduces an efficient way to achieve federated unlearning, by employing a privacy model which allows the FL server to plausibly deny the client's participation in the training up to a certain extent. We demonstrate that the server can generate a Proof-of-Deniability, where each aggregated update can be associated with at least x number of client updates. This enables the server to plausibly deny a client's participation. However, in the event of frequent unlearning requests, the server is required to adopt an unlearning strategy and, accordingly, update its model parameters. We also perturb the client updates in a cluster in order to avoid inference from an honest but curious server. We show that the global model satisfies differential privacy after T number of communication rounds. The proposed methodology has been evaluated on multiple datasets in different privacy settings. The experimental results show that our framework achieves comparable utility while providing a significant reduction in terms of memory (30 times), as well as retraining time (1.6-500769 times). The source code for the paper is available.

Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential inclusion of harmful data samples. Manually filtering or avoiding such samples, however, can be labor-intensive and subjective. To address these difficulties, we propose a novel Safety-Aware Fine-Tuning (SAFT) framework designed to automatically detect and remove potentially harmful data, by leveraging a scoring function that exploits the subspace information of harmful and benign samples. Experimental results demonstrate the efficacy of SAFT across different LLMs and varying contamination rates, achieving reductions in harmfulness of up to 27.8%. Going beyond, we delve into the mechanism of our approach and validate its versatility in addressing practical challenges in real-world scenarios.

Recommender systems play a crucial role in alleviating information overload by providing personalized recommendations tailored to users' preferences and interests. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach for recommender systems, leveraging their ability to effectively capture complex relationships and dependencies between users and items by representing them as nodes in a graph structure. In this study, we investigate the environmental impact of GNN-based recommender systems, an aspect that has been largely overlooked in the literature. Specifically, we conduct a comprehensive analysis of the carbon emissions associated with training and deploying GNN models for recommendation tasks. We evaluate the energy consumption and carbon footprint of different GNN architectures and configurations, considering factors such as model complexity, training duration, hardware specifications and embedding size. By addressing the environmental impact of resource-intensive algorithms in recommender systems, this study contributes to the ongoing efforts towards sustainable and responsible artificial intelligence, promoting the development of eco-friendly recommendation technologies that balance performance and environmental considerations.