The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.

Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) and reducing creditor losses. Traditional methods are labor-intensive, while large language models (LLMs) offer promising automation potential. However, prior systems lacked dynamic negotiation and real-time decision-making capabilities. This paper explores LLMs in automating DCN and proposes a novel evaluation framework with 13 metrics across 4 aspects. Our experiments reveal that LLMs tend to over-concede compared to human negotiators. To address this, we propose the Multi-Agent Debt Negotiation (MADeN) framework, incorporating planning and judging modules to improve decision rationality. We also apply post-training techniques, including DPO with rejection sampling, to optimize performance. Our studies provide valuable insights for practitioners and researchers seeking to enhance efficiency and outcomes in this domain.

Large Language Models (LLMs) show promise as a writing aid for professionals performing legal analyses. However, LLMs can often hallucinate in this setting, in ways difficult to recognize by non-professionals and existing text evaluation metrics. In this work, we pose the question: when can machine-generated legal analysis be evaluated as acceptable? We introduce the neutral notion of gaps, as opposed to hallucinations in a strict erroneous sense, to refer to the difference between human-written and machine-generated legal analysis. Gaps do not always equate to invalid generation. Working with legal experts, we consider the CLERC generation task proposed in Hou et al. (2024b), leading to a taxonomy, a fine-grained detector for predicting gap categories, and an annotated dataset for automatic evaluation. Our best detector achieves 67% F1 score and 80% precision on the test set. Employing this detector as an automated metric on legal analysis generated by SOTA LLMs, we find around 80% contain hallucinations of different kinds.

A loan is money borrowed to someone (the debtor) with the intent to pay back at an agreed date. Ideally, things should go as planned but when the debtor fails to pay the person they borrowed the loan from (the creditor), the debtor is said to have defaulted on the loan. It is then important for creditors/loan companies to know/predict if a certain debtor will default or not. This is a problem that machine learning solves, this is a classification machine learning problem. As with every machine learning problem, data is the major ingredient in solving it.

Automated next-best action recommendation for each customer in a sequential, dynamic and interactive context has been widely needed in natural, social and business decision-making. Personalized next-best action recommendation must involve past, current and future customer demographics and circumstances (states) and behaviors, long-range sequential interactions between customers and decision-makers, multi-sequence interactions between states, behaviors and actions, and their reactions to their counterpart's actions. No existing modeling theories and tools, including Markovian decision processes, user and behavior modeling, deep sequential modeling, and personalized sequential recommendation, can quantify such complex decision-making on a personal level. We take a data-driven approach to learn the next-best actions for personalized decision-making by a reinforced coupled recurrent neural network (CRN). CRN represents multiple coupled dynamic sequences of a customer's historical and current states, responses to decision-makers' actions, decision rewards to actions, and learns long-term multi-sequence interactions between parties (customer and decision-maker). Next-best actions are then recommended on each customer at a time point to change their state for an optimal decision-making objective. Our study demonstrates the potential of personalized deep learning of multi-sequence interactions and automated dynamic intervention for personalized decision-making in complex systems.

Developments in machine learning (ML) and Artificial Intelligence (AI) are having a great impact on the debt collection industry. At its core Machine Learning generates predictive models using algorithms that learn from data. The idea is that if we can input enough useful and reliable data, we can build models which can make predictions on our behalf. There are a number of ways in which machine learning can aid and improve the debt collection process: Reduce Workloads Collections departments place calls, send countless emails, and seek to work out payment plans — and very frequently none of the above activities translate into the successful recovery of debt. With ML this changes. Since tasks are automated, users experience higher productivity and less time spent on labour-intensive tasks. Protecting Your Business Reputation Since ML can automate communication, you know that all your business correspondence will be professional, methodical and unambiguous. LATERAL’S debt collections software provides its users with a non-intrusive, customer-driven point of engagement, which is proven to be highly successful.  

Emails changed the way financial services and law firms used to do business years ago. Now, artificial intelligence is creating a new revolution in the way how law firms and financial institutions work. It is helping to speed up the business process, provide prompt customer service, boost productivity, reduce the workload on human minds, and minimize mistakes. Today, we will discuss how artificial intelligence is helping law firms and financial institutions to boost productivity, reduce expenses, and provide better services to their clients. Artificial intelligence is gradually becoming an indispensable virtual assistant for the lawyers.

Every business seeks to grow. But only a handful of companies that successfully actualize this vision do so through data-based decision making. And to make these informed decisions, companies have been using machine learning-based predictive analytics. Predictive analytics is predicting future outcomes based on historical and current data. It uses various statistical and data modeling techniques to analyze past data, identify trends, and help make informed business decisions.

Every business seeks to grow. But only a handful of companies that successfully actualize this vision do so through data-based decision making. And to make these informed decisions, companies have been using machine learning-based predictive analytics. Predictive analytics is predicting future outcomes based on historical and current data. It uses various statistical and data modeling techniques to analyze past data, identify trends, and help make informed business decisions.

AI works to overcome the limitations of existing, antiquated database systems, through increasing automation and providing compliance management to its users. Furthermore, AI applications focus on productivity and efficiency; they determine the most effective communication method for each debtor, and use machine learning tools to predict and analyse customer behaviour (more on machine learning below). The overall impact is debt recovery and collection is streamlined as a process. The traditional process of debt collection via a human workforce can be incredibly labour intensive, and therefore expensive. Company's collection departments place calls, send emails manually, and manage accounts by updating databases by hand.