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.

In the evolving NLP landscape, benchmarks serve as yardsticks for gauging progress. However, existing Legal NLP benchmarks only focus on predictive tasks, overlooking generative tasks. This work curates LexSumm, a benchmark designed for evaluating legal summarization tasks in English. It comprises eight English legal summarization datasets, from diverse jurisdictions, such as the US, UK, EU and India. Additionally, we release LexT5, legal oriented sequence-to-sequence model, addressing the limitation of the existing BERT-style encoder-only models in the legal domain. We assess its capabilities through zero-shot probing on LegalLAMA and fine-tuning on LexSumm. Our analysis reveals abstraction and faithfulness errors even in summaries generated by zero-shot LLMs, indicating opportunities for further improvements. LexSumm benchmark and LexT5 model are available at https://github.com/TUMLegalTech/LexSumm-LexT5.

Large Language Models (LLMs) perform outstandingly in various downstream tasks, and the use of the Retrieval-Augmented Generation (RAG) architecture has been shown to improve performance for legal question answering (Nuruzzaman and Hussain, 2020; Louis et al., 2024). However, there are limited applications in insurance questions-answering, a specific type of legal document. This paper introduces two corpora: the Quebec Automobile Insurance Expertise Reference Corpus and a set of 82 Expert Answers to Layperson Automobile Insurance Questions. Our study leverages both corpora to automatically and manually assess a GPT4-o, a state-of-the-art LLM, to answer Quebec automobile insurance questions. Our results demonstrate that, on average, using our expertise reference corpus generates better responses on both automatic and manual evaluation metrics. However, they also highlight that LLM QA is unreliable enough for mass utilization in critical areas. Indeed, our results show that between 5% to 13% of answered questions include a false statement that could lead to customer misunderstanding.

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases even when they pass explicit bias evaluations. Building upon the frameworks of the LLM Implicit Association Test (IAT) Bias and LLM Decision Bias, this study highlights that newer or larger language models do not automatically exhibit reduced bias; in some cases, they displayed higher bias scores than their predecessors, such as in Meta's Llama series and OpenAI's GPT models. This suggests that increasing model complexity without deliberate bias mitigation strategies can unintentionally amplify existing biases. The variability in bias scores within and across providers underscores the need for standardized evaluation metrics and benchmarks for bias assessment. The lack of consistency indicates that bias mitigation is not yet a universally prioritized goal in model development, which can lead to unfair or discriminatory outcomes. By broadening the detection of implicit bias, this research provides a more comprehensive understanding of the biases present in advanced models and underscores the critical importance of addressing these issues to ensure the development of fair and responsible AI systems.

Patents are the currency of innovation, and like any currency, they need to be managed and protected (Gavin Potenza). Patents, as legal documents that secure intellectual property rights, play a critical role in technological innovation. The growing complexity of patent documents and the surge in patent applications have created a need for automated solutions in patent analysis. In this work, we present PatExpert, an autonomous multi-agent conversational framework designed to streamline and optimize patent-related tasks. The framework consists of a metaagent that coordinates task-specific expert agents for various patent-related tasks and a critique agent for error handling and feedback provision. The meta-agent orchestrates specialized expert agents, each fine-tuned for specific tasks such as patent classification, acceptance, claim generation, abstractive summarization, multi-patent analysis, and scientific hypothesis generation. For multi-patent analysis, the framework incorporates advanced methods like Graph Retrieval-Augmented Generation (GRAG) to enhance response accuracy and relevance by combining semantic similarity with knowledge graphs. Error handling is managed by critique agents (Gold-LLM-as-a-Judge and Reward-LLM-as-a-Judge), which evaluate output responses for accuracy and provide iterative feedback. The framework also prioritizes explainability, ensuring transparent justifications for decisions made during patent analysis. Its comprehensive capabilities make it a valuable tool for automating complex patent workflows, enhancing efficiency, accuracy, and compliance in patent-related tasks. Empirical evidence demonstrates significant improvements in patent processing tasks, concluding that the framework offers a robust solution for automating and optimizing patent analysis.

``When a measure becomes a target, it ceases to be a good measure'', this adage is known as {\it Goodhart's law}. In this paper, we investigate formally this law and prove that it critically depends on the tail distribution of the discrepancy between the true goal and the measure that is optimized. Discrepancies with long-tail distributions favor a Goodhart's law, that is, the optimization of the measure can have a counter-productive effect on the goal. We provide a formal setting to assess Goodhart's law by studying the asymptotic behavior of the correlation between the goal and the measure, as the measure is optimized. Moreover, we introduce a distinction between a {\it weak} Goodhart's law, when over-optimizing the metric is useless for the true goal, and a {\it strong} Goodhart's law, when over-optimizing the metric is harmful for the true goal. A distinction which we prove to depend on the tail distribution. We stress the implications of this result to large-scale decision making and policies that are (and have to be) based on metrics, and propose numerous research directions to better assess the safety of such policies in general, and to the particularly concerning case where these policies are automated with algorithms.