Large Language Models (LLMs) have shown remarkable capabilities in a multitude of Natural Language Processing (NLP) tasks. However, these models are still not immune to limitations such as social biases, especially gender bias. This work investigates whether current closed and open-source LLMs possess gender bias, especially when asked to give moral opinions. To evaluate these models, we curate and introduce a new dataset GenMO (Gender-bias in Morality Opinions) comprising parallel short stories featuring male and female characters respectively. Specifically, we test models from the GPT family (GPT-3.5-turbo, GPT-3.5-turbo-instruct, GPT-4-turbo), Llama 3 and 3.1 families (8B/70B), Mistral-7B and Claude 3 families (Sonnet and Opus). Surprisingly, despite employing safety checks, all production-standard models we tested display significant gender bias with GPT-3.5-turbo giving biased opinions in 24% of the samples. Additionally, all models consistently favour female characters, with GPT showing bias in 68-85% of cases and Llama 3 in around 81-85% instances. Additionally, our study investigates the impact of model parameters on gender bias and explores real-world situations where LLMs reveal biases in moral decision-making.

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.

Retrieval-based question answering systems often suffer from positional bias, leading to suboptimal answer generation. We propose LoRE (Logit-Ranked Retriever Ensemble), a novel approach that improves answer accuracy and relevance by mitigating positional bias. LoRE employs an ensemble of diverse retrievers, such as BM25 and sentence transformers with FAISS indexing. A key innovation is a logit-based answer ranking algorithm that combines the logit scores from a large language model (LLM), with the retrieval ranks of the passages. Experimental results on NarrativeQA, SQuAD demonstrate that LoRE significantly outperforms existing retrieval-based methods in terms of exact match and F1 scores. On SQuAD, LoRE achieves 14.5\%, 22.83\%, and 14.95\% improvements over the baselines for ROUGE-L, EM, and F1, respectively. Qualitatively, LoRE generates more relevant and accurate answers, especially for complex queries.

The Mutual Reinforcement Effect (MRE) investigates the synergistic relationship between word-level and text-level classifications in text classification tasks. It posits that the performance of both classification levels can be mutually enhanced. However, this mechanism has not been adequately demonstrated or explained in prior research. To address this gap, we employ empirical experiment to observe and substantiate the MRE theory. Our experiments on 21 MRE mix datasets revealed the presence of MRE in the model and its impact. Specifically, we conducted compare experiments use fine-tune. The results of findings from comparison experiments corroborates the existence of MRE. Furthermore, we extended the application of MRE to prompt learning, utilizing word-level information as a verbalizer to bolster the model's prediction of text-level classification labels. In our final experiment, the F1-score significantly surpassed the baseline in 18 out of 21 MRE Mix datasets, further validating the notion that word-level information enhances the language model's comprehension of the text as a whole.

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.

Parameter-efficient fine-tuning (PEFT) of large language models (LLMs) has gained considerable attention as a flexible and efficient way of adapting LLMs to downstream tasks. Among these methods, weighted decomposed low-rank adaptation (DoRA) has emerged as a promising approach. DoRA bridges the gap between low-rank adaptation (LoRA) and full fine-tuning (FT) by decomposing the weight matrices into magnitude and direction components, thereby maintaining learning behavior similar to FT. Although DoRA shows encouraging performance, it introduces additional parameters compared to LoRA, which potentially increases the risk of overfitting. Moreover, optimizing magnitude and direction simultaneously leads to a coupled gradient updating pattern for both components, limiting its learning capacity. To overcome these limitations, we propose BiDoRA, a bi-level optimization-based PEFT method. In BiDoRA, the direction and magnitude components are optimized on two distinct datasets at different optimization levels, mitigating the risk of overfitting. Additionally, the asynchronous optimization of the two components promotes their decoupling, allowing for more flexible gradient updates suitable for various downstream tasks. Evaluation of BiDoRA on fourteen datasets spanning natural language understanding, natural language generation, and token classification reveals that it significantly outperforms DoRA and other PEFT methods. The superior performance of BiDoRA underscores its effectiveness. The code for BiDoRA is available at https://anonymous.4open.science/r/BiDoRA-5D31.

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that LLMs trained with Reinforcement Learning from Human Feedback (RLHF) are overconfident with a more sharpened output probability, in this study, we reveal that RLHF tends to lead models to express verbalized overconfidence in their own responses. We investigate the underlying cause of this overconfidence and demonstrate that reward models used for Proximal Policy Optimization (PPO) exhibit inherent biases towards high-confidence scores regardless of the actual quality of responses. Building upon this insight, we propose two PPO variants: PPO-M: PPO with Calibrated Reward Modeling and PPO-C: PPO with Calibrated Reward Calculation. PPO-M integrates explicit confidence scores in reward model training, which calibrates reward models to better capture the alignment between response quality and verbalized confidence. PPO-C adjusts the reward score during PPO based on the difference between the current reward and the moving average of past rewards. Both PPO-M and PPO-C can be seamlessly integrated into the current PPO pipeline and do not require additional golden labels. We evaluate our methods on both Llama3-8B and Mistral-7B across six diverse datasets including multiple-choice and open-ended generation. Experiment results demonstrate that both of our methods can reduce calibration error and maintain performance comparable to standard PPO. We further show that they do not compromise model capabilities in open-ended conversation settings.

Recently, there has been a growing trend of employing large language models (LLMs) to judge the quality of other LLMs. Many studies have adopted closed-source models, mainly using GPT-4 as the evaluator. However, due to the closed-source nature of the GPT-4 model, employing it as an evaluator has resulted in issues including transparency, controllability, and cost-effectiveness. Some researchers have turned to using fine-tuned open-source LLMs as evaluators. However, existing open-source evaluation LLMs generally lack a user-friendly visualization tool, and they have not been optimized for accelerated model inference, which causes inconvenience for researchers with limited resources and those working across different fields. This paper presents EasyJudge, a model developed to evaluate significant language model responses. It is lightweight, precise, efficient, and user-friendly, featuring an intuitive visualization interface for ease of deployment and use. EasyJudge uses detailed datasets and refined prompts for model optimization, achieving strong consistency with human and proprietary model evaluations. The model optimized with quantitative methods enables EasyJudge to run efficiently on consumer-grade GPUs or even CPUs. We also provide detailed analysis and case studies to further reveal the potential of our method.

In recent years, large language models have demonstrated remarkable capabilities in natural language understanding and generation. However, these models often struggle with hallucinations and maintaining long term contextual relevance, particularly when dealing with private or local data. This paper presents a novel architecture that addresses these challenges by integrating an orchestration engine that utilizes multiple LLMs in conjunction with a temporal graph database and a vector database. The proposed system captures user interactions, builds a graph representation of conversations, and stores nodes and edges that map associations between key concepts, entities, and behaviors over time. This graph based structure allows the system to develop an evolving understanding of the user preferences, providing personalized and contextually relevant answers. In addition to this, a vector database encodes private data to supply detailed information when needed, allowing the LLM to access and synthesize complex responses. To further enhance reliability, the orchestration engine coordinates multiple LLMs to generate comprehensive answers and iteratively reflect on their accuracy. The result is an adaptive, privacy centric AI assistant capable of offering deeper, more relevant interactions while minimizing the risk of hallucinations. This paper outlines the architecture, methodology, and potential applications of this system, contributing a new direction in personalized, context aware AI assistance.

Dysarthria is a motor speech disorder caused by neurological damage that affects the muscles used for speech production, leading to slurred, slow, or difficult-to-understand speech. It affects millions of individuals worldwide, including those with conditions such as stroke, traumatic brain injury, cerebral palsy, Parkinsons disease, and multiple sclerosis. Dysarthria presents a major communication barrier, impacting quality of life and social interaction. This paper introduces a novel approach to recognizing and translating dysarthric speech, empowering individuals with this condition to communicate more effectively. We leverage advanced large language models for accurate speech correction and multimodal emotion analysis. Dysarthric speech is first converted to text using OpenAI Whisper model, followed by sentence prediction using fine-tuned open-source models and benchmark models like GPT-4.o, LLaMA 3.1 70B and Mistral 8x7B on Groq AI accelerators. The dataset used combines the TORGO dataset with Google speech data, manually labeled for emotional context. Our framework identifies emotions such as happiness, sadness, neutrality, surprise, anger, and fear, while reconstructing intended sentences from distorted speech with high accuracy. This approach demonstrates significant advancements in the recognition and interpretation of dysarthric speech.