Transfer learning in Reinforcement Learning (RL) enables agents to leverage knowledge from source tasks to accelerate learning in target tasks. While prior work, such as the Attend, Adapt, and Transfer (A2T) framework, addresses negative transfer and selective transfer, other critical challenges remain underexplored. This paper introduces the Generalized Adaptive Transfer Network (GATN), a deep RL architecture designed to tackle task generalization across domains, robustness to environmental changes, and computational efficiency in transfer. GATN employs a domain-agnostic representation module, a robustness-aware policy adapter, and an efficient transfer scheduler to achieve these goals. We evaluate GATN on diverse benchmarks, including Atari 2600, MuJoCo, and a custom chatbot dialogue environment, demonstrating superior performance in cross-domain generalization, resilience to dynamic environments, and reduced computational overhead compared to baselines. Our findings suggest GATN is a versatile framework for real-world RL applications, such as adaptive chatbots and robotic control.
As the capabilities of chatbots and their underlying LLMs continue to dramatically improve, evaluating their performance has increasingly become a major blocker to their further development. A major challenge is the available benchmarking datasets, which are largely static, outdated, and lacking in multilingual coverage, limiting their ability to capture subtle linguistic and cultural variations. This paper introduces MEDAL, an automated multi-agent framework for generating, evaluating, and curating more representative and diverse open-domain dialogue evaluation benchmarks. Our approach leverages several state-of-the-art LLMs to generate user-chatbot multilingual dialogues, conditioned on varied seed contexts. A strong LLM (GPT-4.1) is then used for a multidimensional analysis of the performance of the chatbots, uncovering noticeable cross-lingual performance differences. Guided by this large-scale evaluation, we curate a new meta-evaluation multilingual benchmark and human-annotate samples with nuanced quality judgments. This benchmark is then used to assess the ability of several reasoning and non-reasoning LLMs to act as evaluators of open-domain dialogues. We find that current LLMs struggle to detect nuanced issues, particularly those involving empathy and reasoning.
State-of-the-art large language models require specialized hardware and substantial energy to operate. As a consequence, cloud-based services that provide access to large language models have become very popular. In these services, the price users pay for an output provided by a model depends on the number of tokens the model uses to generate it -- they pay a fixed price per token. In this work, we show that this pricing mechanism creates a financial incentive for providers to strategize and misreport the (number of) tokens a model used to generate an output, and users cannot prove, or even know, whether a provider is overcharging them. However, we also show that, if an unfaithful provider is obliged to be transparent about the generative process used by the model, misreporting optimally without raising suspicion is hard. Nevertheless, as a proof-of-concept, we introduce an efficient heuristic algorithm that allows providers to significantly overcharge users without raising suspicion, highlighting the vulnerability of users under the current pay-per-token pricing mechanism. Further, to completely eliminate the financial incentive to strategize, we introduce a simple incentive-compatible token pricing mechanism. Under this mechanism, the price users pay for an output provided by a model depends on the number of characters of the output -- they pay a fixed price per character. Along the way, to illustrate and complement our theoretical results, we conduct experiments with several large language models from the $\texttt{Llama}$, $\texttt{Gemma}$ and $\texttt{Ministral}$ families, and input prompts from the LMSYS Chatbot Arena platform.
The conversational capabilities of Large Language Models (LLMs) suggest that they may be able to perform as automated talk therapists. It is crucial to know if these systems would be effective and adhere to known standards. We present a counsellor chatbot that focuses on motivating tobacco smokers to quit smoking. It uses a state-of-the-art LLM and a widely applied therapeutic approach called Motivational Interviewing (MI), and was evolved in collaboration with clinician-scientists with expertise in MI. We also describe and validate an automated assessment of both the chatbot's adherence to MI and client responses. The chatbot was tested on 106 participants, and their confidence that they could succeed in quitting smoking was measured before the conversation and one week later. Participants' confidence increased by an average of 1.7 on a 0-10 scale. The automated assessment of the chatbot showed adherence to MI standards in 98% of utterances, higher than human counsellors. The chatbot scored well on a participant-reported metric of perceived empathy but lower than typical human counsellors. Furthermore, participants' language indicated a good level of motivation to change, a key goal in MI. These results suggest that the automation of talk therapy with a modern LLM has promise.
LLM-based multi-agent systems (MAS) extend the capabilities of single LLMs by enabling cooperation among multiple specialized agents. However, most existing MAS frameworks rely on a single LLM to drive all agents, constraining the system's intelligence to the limit of that model. This paper explores the paradigm of heterogeneous LLM-driven MAS (X-MAS), where agents are powered by diverse LLMs, elevating the system's potential to the collective intelligence of diverse LLMs. We introduce X-MAS-Bench, a comprehensive testbed designed to evaluate the performance of various LLMs across different domains and MAS-related functions. As an extensive empirical study, we assess 27 LLMs across 5 domains (encompassing 21 test sets) and 5 functions, conducting over 1.7 million evaluations to identify optimal model selections for each domain-function combination. Building on these findings, we demonstrate that transitioning from homogeneous to heterogeneous LLM-driven MAS can significantly enhance system performance without requiring structural redesign. Specifically, in a chatbot-only MAS scenario, the heterogeneous configuration yields up to 8.4\% performance improvement on the MATH dataset. In a mixed chatbot-reasoner scenario, the heterogeneous MAS could achieve a remarkable 47\% performance boost on the AIME dataset. Our results underscore the transformative potential of heterogeneous LLMs in MAS, highlighting a promising avenue for advancing scalable, collaborative AI systems.
Large Language Models (LLMs) have shown strong capability in diverse software engineering tasks, e.g. code completion, bug fixing, and document generation. However, feature-driven development (FDD), a highly prevalent real-world task that involves developing new functionalities for large, existing codebases, remains underexplored. We therefore introduce SWE-Dev, the first large-scale dataset (with 14,000 training and 500 test samples) designed to evaluate and train autonomous coding systems on real-world feature development tasks. To ensure verifiable and diverse training, SWE-Dev uniquely provides all instances with a runnable environment and its developer-authored executable unit tests. This collection not only provides high-quality data for Supervised Fine-Tuning (SFT), but also enables Reinforcement Learning (RL) by delivering accurate reward signals from executable unit tests. Our extensive evaluations on SWE-Dev, covering 17 chatbot LLMs, 10 reasoning models, and 10 Multi-Agent Systems (MAS), reveal that FDD is a profoundly challenging frontier for current AI (e.g., Claude-3.7-Sonnet achieves only 22.45\% Pass@3 on the hard test split). Crucially, we demonstrate that SWE-Dev serves as an effective platform for model improvement: fine-tuning on training set enabled a 7B model comparable to GPT-4o on \textit{hard} split, underscoring the value of its high-quality training data. Code is available here \href{https://github.com/DorothyDUUU/SWE-Dev}{https://github.com/DorothyDUUU/SWE-Dev}.
Mental-health stigma remains a pervasive social problem that hampers treatment-seeking and recovery. Existing resources for training neural models to finely classify such stigma are limited, relying primarily on social-media or synthetic data without theoretical underpinnings. To remedy this gap, we present an expert-annotated, theory-informed corpus of human-chatbot interviews, comprising 4,141 snippets from 684 participants with documented socio-cultural backgrounds. Our experiments benchmark state-of-the-art neural models and empirically unpack the challenges of stigma detection. This dataset can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma. Our corpus is openly available at https://github.com/HanMeng2004/Mental-Health-Stigma-Interview-Corpus.
The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (eg MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (eg Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (eg LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few "authority" models. To tackle these issues, we propose Decentralized Arena (dearena), a fully automated framework leveraging collective intelligence from all LLMs to evaluate each other. It mitigates single-model judge bias by democratic, pairwise evaluation, and remains efficient at scale through two key components: (1) a coarse-to-fine ranking algorithm for fast incremental insertion of new models with sub-quadratic complexity, and (2) an automatic question selection strategy for the construction of new evaluation dimensions. Across extensive experiments across 66 LLMs, dearena attains up to 97% correlation with human judgements, while significantly reducing the cost. Our code and data will be publicly released on https://github.com/maitrix-org/de-arena.
Knowledge Graphs have become increasingly popular due to their wide usage in various downstream applications, including information retrieval, chatbot development, language model construction, and many others. Link prediction (LP) is a crucial downstream task for knowledge graphs, as it helps to address the problem of the incompleteness of the knowledge graphs. However, previous research has shown that knowledge graphs, often created in a (semi) automatic manner, are not free from social biases. These biases can have harmful effects on downstream applications, especially by leading to unfair behavior toward minority groups. To understand this issue in detail, we develop a framework -- AuditLP -- deploying fairness metrics to identify biased outcomes in LP, specifically how occupations are classified as either male or female-dominated based on gender as a sensitive attribute. We have experimented with the sensitive attribute of age and observed that occupations are categorized as young-biased, old-biased, and age-neutral. We conduct our experiments on a large number of knowledge triples that belong to 21 different geographies extracted from the open-sourced knowledge graph, Wikidata. Our study shows that the variance in the biased outcomes across geographies neatly mirrors the socio-economic and cultural division of the world, resulting in a transparent partition of the Global North from the Global South.
Real-time, intelligent, and natural speech interaction is an essential part of the next-generation human-computer interaction. Recent advancements have showcased the potential of building intelligent spoken chatbots based on large language models (LLMs). In this paper, we introduce LLaMA-Omni 2, a series of speech language models (SpeechLMs) ranging from 0.5B to 14B parameters, capable of achieving high-quality real-time speech interaction. LLaMA-Omni 2 is built upon the Qwen2.5 series models, integrating a speech encoder and an autoregressive streaming speech decoder. Despite being trained on only 200K multi-turn speech dialogue samples, LLaMA-Omni 2 demonstrates strong performance on several spoken question answering and speech instruction following benchmarks, surpassing previous state-of-the-art SpeechLMs like GLM-4-Voice, which was trained on millions of hours of speech data.
Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. In this paper, we identify a model preference bias in RMs, where they systematically assign disproportionately high scores to responses from certain policy models. This bias distorts ranking evaluations and leads to unfair judgments. To address this issue, we propose a calibration method named CHatbot Arena calibrated Reward Modeling (CHARM) that leverages Elo scores from the Chatbot Arena leaderboard to mitigate RM overvaluation. We also introduce a Mismatch Degree metric to measure this preference bias. Our approach is computationally efficient, requiring only a small preference dataset for continued training of the RM. We conduct extensive experiments on reward model benchmarks and human preference alignment. Results demonstrate that our calibrated RMs (1) achieve improved evaluation accuracy on RM-Bench and the Chat-Hard domain of RewardBench, and (2) exhibit a stronger correlation with human preferences by producing scores more closely aligned with Elo rankings. By mitigating model preference bias, our method provides a generalizable and efficient solution for building fairer and more reliable reward models.
Cancer patients are increasingly turning to large language models (LLMs) as a new form of internet search for medical information, making it critical to assess how well these models handle complex, personalized questions. However, current medical benchmarks focus on medical exams or consumer-searched questions and do not evaluate LLMs on real patient questions with detailed clinical contexts. In this paper, we first evaluate LLMs on cancer-related questions drawn from real patients, reviewed by three hematology oncology physicians. While responses are generally accurate, with GPT-4-Turbo scoring 4.13 out of 5, the models frequently fail to recognize or address false presuppositions in the questions-posing risks to safe medical decision-making. To study this limitation systematically, we introduce Cancer-Myth, an expert-verified adversarial dataset of 585 cancer-related questions with false presuppositions. On this benchmark, no frontier LLM -- including GPT-4o, Gemini-1.Pro, and Claude-3.5-Sonnet -- corrects these false presuppositions more than 30% of the time. Even advanced medical agentic methods do not prevent LLMs from ignoring false presuppositions. These findings expose a critical gap in the clinical reliability of LLMs and underscore the need for more robust safeguards in medical AI systems.
Collaborative assistants, or chatbots, are data-driven decision support systems that enable natural interaction for task completion. While they can meet critical needs in modern society, concerns about their reliability and trustworthiness persist. In particular, Large Language Model (LLM)-based chatbots like ChatGPT, Gemini, and DeepSeek are becoming more accessible. However, such chatbots have limitations, including their inability to explain response generation, the risk of generating problematic content, the lack of standardized testing for reliability, and the need for deep AI expertise and extended development times. These issues make chatbots unsuitable for trust-sensitive applications like elections or healthcare. To address these concerns, we introduce SafeChat, a general architecture for building safe and trustworthy chatbots, with a focus on information retrieval use cases. Key features of SafeChat include: (a) safety, with a domain-agnostic design where responses are grounded and traceable to approved sources (provenance), and 'do-not-respond' strategies to prevent harmful answers; (b) usability, with automatic extractive summarization of long responses, traceable to their sources, and automated trust assessments to communicate expected chatbot behavior, such as sentiment; and (c) fast, scalable development, including a CSV-driven workflow, automated testing, and integration with various devices. We implemented SafeChat in an executable framework using the open-source chatbot platform Rasa. A case study demonstrates its application in building ElectionBot-SC, a chatbot designed to safely disseminate official election information. SafeChat is being used in many domains, validating its potential, and is available at: https://github.com/ai4society/trustworthy-chatbot.
An ideal model evaluation should achieve two goals: identifying where the model fails and providing actionable improvement guidance. Toward these goals for Language Model (LM) evaluations, we formulate the problem of generating a weakness profile, a set of weaknesses expressed in natural language, given an LM's performance on every individual instance in a benchmark. We introduce a suite of quantitative assessments to compare different weakness profiling methods. We also propose a weakness profiling method EvalTree. It constructs a capability tree where each node represents a capability described in natural language and is linked to a subset of benchmark instances that specifically evaluate this capability; it then extracts nodes where the LM performs poorly to generate a weakness profile. On the MATH and WildChat benchmarks, we show that EvalTree outperforms baseline weakness profiling methods by identifying weaknesses more precisely and comprehensively. Weakness profiling further enables weakness-guided data collection, and training data collection guided by EvalTree-identified weaknesses improves LM performance more than other data collection strategies. We also show how EvalTree exposes flaws in Chatbot Arena's human-voter-based evaluation practice. To facilitate future work, we release our code and an interface that allows practitioners to interactively explore the capability trees built by EvalTree.
Teaching literature under interdisciplinary contexts (e.g., science, art) that connect reading materials has become popular in elementary schools. However, constructing such contexts is challenging as it requires teachers to explore substantial amounts of interdisciplinary content and link it to the reading materials. In this paper, we develop LitLinker via an iterative design process involving 13 teachers to facilitate the ideation of interdisciplinary contexts for teaching literature. Powered by a large language model (LLM), LitLinker can recommend interdisciplinary topics and contextualize them with the literary elements (e.g., paragraphs, viewpoints) in the reading materials. A within-subjects study (N=16) shows that compared to an LLM chatbot, LitLinker can improve the integration depth of different subjects and reduce workload in this ideation task. Expert interviews (N=9) also demonstrate LitLinker's usefulness for supporting the ideation of interdisciplinary contexts for teaching literature. We conclude with concerns and design considerations for supporting interdisciplinary teaching with LLMs.
Large language model (LLM) evaluations typically rely on aggregated metrics like accuracy or human preference, averaging across users and prompts. This averaging obscures user- and prompt-specific variations in model performance. To address this, we propose Prompt-to-Leaderboard (P2L), a method that produces leaderboards specific to a prompt. The core idea is to train an LLM taking natural language prompts as input to output a vector of Bradley-Terry coefficients which are then used to predict the human preference vote. The resulting prompt-dependent leaderboards allow for unsupervised task-specific evaluation, optimal routing of queries to models, personalization, and automated evaluation of model strengths and weaknesses. Data from Chatbot Arena suggest that P2L better captures the nuanced landscape of language model performance than the averaged leaderboard. Furthermore, our findings suggest that P2L's ability to produce prompt-specific evaluations follows a power law scaling similar to that observed in LLMs themselves. In January 2025, the router we trained based on this methodology achieved the \#1 spot in the Chatbot Arena leaderboard. Our code is available at this GitHub link: https://github.com/lmarena/p2l.
Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset. However, DPO has the limitation that the KL penalty, which prevents excessive deviation from the reference model, is static throughout the training process. Several methods claim to change this static KL penalty of DPO into a dynamic one, but no approach can adaptively assign different KL penalties for each preference pair. In this paper, we propose $\varepsilon$-Direct Preference Optimization ($\varepsilon$-DPO), which allows adaptive control of the KL penalty strength $\beta$ for each preference pair. Specifically, $\varepsilon$-DPO adaptively controls $\beta$ for each preference pair based on the monotonicity of logits as a preference model under the perturbation of $\beta$ during training. This is equivalent to adjusting the KL penalty by checking whether the change in training-time temperature can lead to better preference confidence as preference models by simply reusing the logit of the current policy and the reference policy. Experimental results show that the simple criterion of $\varepsilon$-DPO for KL penalty relaxation significantly improves DPO compared to most existing direct alignment algorithms on general chatbot benchmarks and reveal that this KL penalty control criterion can reflect confusion as a preference model and provide an efficient KL trade-off, highlighting the significance of instance-level adaptive KL penalty control in DPO.
Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.
Names are deeply tied to human identity. They can serve as markers of individuality, cultural heritage, and personal history. However, using names as a core indicator of identity can lead to over-simplification of complex identities. When interacting with LLMs, user names are an important point of information for personalisation. Names can enter chatbot conversations through direct user input (requested by chatbots), as part of task contexts such as CV reviews, or as built-in memory features that store user information for personalisation. We study biases associated with names by measuring cultural presumptions in the responses generated by LLMs when presented with common suggestion-seeking queries, which might involve making assumptions about the user. Our analyses demonstrate strong assumptions about cultural identity associated with names present in LLM generations across multiple cultures. Our work has implications for designing more nuanced personalisation systems that avoid reinforcing stereotypes while maintaining meaningful customisation.
Large language models (LLMs) have significantly advanced the field of natural language generation. However, they frequently generate unverified outputs, which compromises their reliability in critical applications. In this study, we propose an innovative framework that combines structured biomedical knowledge with LLMs through a retrieval-augmented generation technique. Our system develops a thorough knowledge graph by identifying and refining causal relationships and named entities from medical abstracts related to age-related macular degeneration (AMD). Using a vector-based retrieval process and a locally deployed language model, our framework produces responses that are both contextually relevant and verifiable, with direct references to clinical evidence. Experimental results show that this method notably decreases hallucinations, enhances factual precision, and improves the clarity of generated responses, providing a robust solution for advanced biomedical chatbot applications.