Large Language Models (LLMs) excel at many tasks but struggle with ambiguous scenarios where multiple valid responses exist, often yielding unreliable results. Conversely, Small Language Models (SLMs) demonstrate robustness in such scenarios but are susceptible to misleading or adversarial inputs. We observed that LLMs handle negative examples effectively, while SLMs excel with positive examples. To leverage their complementary strengths, we introduce SLIDE (Small and Large Integrated for Dialogue Evaluation), a method integrating SLMs and LLMs via adaptive weighting. Building on SLIDE, we further propose a Dual-Refinement Evaluation (DRE) method to enhance SLM-LLM integration: (1) SLM-generated insights guide the LLM to produce initial evaluations; (2) SLM-derived adjustments refine the LLM's scores for improved accuracy. Experiments demonstrate that DRE outperforms existing methods, showing stronger alignment with human judgment across diverse benchmarks. This work illustrates how combining small and large models can yield more reliable evaluation tools, particularly for open-ended tasks such as dialogue evaluation.
Large Language Models (\textbf{LLMs}), e.g. ChatGPT, have been widely adopted in real-world dialogue applications. However, LLMs' robustness, especially in handling long complex dialogue sessions, including frequent motivation transfer, sophisticated cross-turn dependency, is criticized all along. Nevertheless, no existing benchmarks can fully reflect these weaknesses. We present \textbf{MARS-Bench}, a \textbf{M}ulti-turn \textbf{A}thletic \textbf{R}eal-world \textbf{S}cenario Dialogue \textbf{Bench}mark, designed to remedy the gap. MARS-Bench is constructed from play-by-play text commentary so to feature realistic dialogues specifically designed to evaluate three critical aspects of multi-turn conversations: Ultra Multi-turn, Interactive Multi-turn, and Cross-turn Tasks. Extensive experiments on MARS-Bench also reveal that closed-source LLMs significantly outperform open-source alternatives, explicit reasoning significantly boosts LLMs' robustness on handling long complex dialogue sessions, and LLMs indeed face significant challenges when handling motivation transfer and sophisticated cross-turn dependency. Moreover, we provide mechanistic interpretability on how attention sinks due to special tokens lead to LLMs' performance degradation when handling long complex dialogue sessions based on attention visualization experiment in Qwen2.5-7B-Instruction.
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.
Legal consultation is essential for safeguarding individual rights and ensuring access to justice, yet remains costly and inaccessible to many individuals due to the shortage of professionals. While recent advances in Large Language Models (LLMs) offer a promising path toward scalable, low-cost legal assistance, current systems fall short in handling the interactive and knowledge-intensive nature of real-world consultations. To address these challenges, we introduce LeCoDe, a real-world multi-turn benchmark dataset comprising 3,696 legal consultation dialogues with 110,008 dialogue turns, designed to evaluate and improve LLMs' legal consultation capability. With LeCoDe, we innovatively collect live-streamed consultations from short-video platforms, providing authentic multi-turn legal consultation dialogues. The rigorous annotation by legal experts further enhances the dataset with professional insights and expertise. Furthermore, we propose a comprehensive evaluation framework that assesses LLMs' consultation capabilities in terms of (1) clarification capability and (2) professional advice quality. This unified framework incorporates 12 metrics across two dimensions. Through extensive experiments on various general and domain-specific LLMs, our results reveal significant challenges in this task, with even state-of-the-art models like GPT-4 achieving only 39.8% recall for clarification and 59% overall score for advice quality, highlighting the complexity of professional consultation scenarios. Based on these findings, we further explore several strategies to enhance LLMs' legal consultation abilities. Our benchmark contributes to advancing research in legal domain dialogue systems, particularly in simulating more real-world user-expert interactions.
Recent advancements in large language models (LLMs) have revolutionized their ability to handle single-turn tasks, yet real-world applications demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent advancements in evaluating and enhancing multi-turn interactions in LLMs. Focusing on task-specific scenarios, from instruction following in diverse domains such as math and coding to complex conversational engagements in roleplay, healthcare, education, and even adversarial jailbreak settings, we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness over prolonged dialogues. The paper organizes current benchmarks and datasets into coherent categories that reflect the evolving landscape of multi-turn dialogue evaluation. In addition, we review a range of enhancement methodologies under multi-turn settings, including model-centric strategies (contextual learning, supervised fine-tuning, reinforcement learning, and new architectures), external integration approaches (memory-augmented, retrieval-based methods, and knowledge graph), and agent-based techniques for collaborative interactions. Finally, we discuss open challenges and propose future directions for research to further advance the robustness and effectiveness of multi-turn interactions in LLMs. Related resources and papers are available at https://github.com/yubol-cmu/Awesome-Multi-Turn-LLMs.
In this paper, we describe our participation in the RuTermEval competition devoted to extracting nested terms. We apply the Binder model, which was previously successfully applied to the recognition of nested named entities, to extract nested terms. We obtained the best results of term recognition in all three tracks of the RuTermEval competition. In addition, we study the new task of recognition of nested terms from flat training data annotated with terms without nestedness. We can conclude that several approaches we proposed in this work are viable enough to retrieve nested terms effectively without nested labeling of them.
In this paper, we introduce the Dialogue Evaluation shared task on extraction of structured opinions from Russian news texts. The task of the contest is to extract opinion tuples for a given sentence; the tuples are composed of a sentiment holder, its target, an expression and sentiment from the holder to the target. In total, the task received more than 100 submissions. The participants experimented mainly with large language models in zero-shot, few-shot and fine-tuning formats. The best result on the test set was obtained with fine-tuning of a large language model. We also compared 30 prompts and 11 open source language models with 3-32 billion parameters in the 1-shot and 10-shot settings and found the best models and prompts.
The standard language modeling (LM) loss by itself has been shown to be inadequate for effective dialogue modeling. As a result, various training approaches, such as auxiliary loss functions and leveraging human feedback, are being adopted to enrich open-domain dialogue systems. One such auxiliary loss function is Bag-of-Words (BoW) loss, defined as the cross-entropy loss for predicting all the words/tokens of the next utterance. In this work, we propose a novel auxiliary loss named Bag-of-Keywords (BoK) loss to capture the central thought of the response through keyword prediction and leverage it to enhance the generation of meaningful and interpretable responses in open-domain dialogue systems. BoK loss upgrades the BoW loss by predicting only the keywords or critical words/tokens of the next utterance, intending to estimate the core idea rather than the entire response. We incorporate BoK loss in both encoder-decoder (T5) and decoder-only (DialoGPT) architecture and train the models to minimize the weighted sum of BoK and LM (BoK-LM) loss. We perform our experiments on two popular open-domain dialogue datasets, DailyDialog and Persona-Chat. We show that the inclusion of BoK loss improves the dialogue generation of backbone models while also enabling post-hoc interpretability. We also study the effectiveness of BoK-LM loss as a reference-free metric and observe comparable performance to the state-of-the-art metrics on various dialogue evaluation datasets.
Advancements in dialogue systems powered by large language models (LLMs) have outpaced the development of reliable evaluation metrics, particularly for diverse and creative responses. We present a benchmark for evaluating the robustness of reference-free dialogue metrics against four categories of adversarial attacks: speaker tag prefixes, static responses, ungrammatical responses, and repeated conversational context. We analyze metrics such as DialogRPT, UniEval, and PromptEval -- a prompt-based method leveraging LLMs -- across grounded and ungrounded datasets. By examining both their correlation with human judgment and susceptibility to adversarial attacks, we find that these two axes are not always aligned; metrics that appear to be equivalent when judged by traditional benchmarks may, in fact, vary in their scores of adversarial responses. These findings motivate the development of nuanced evaluation frameworks to address real-world dialogue challenges.
As dialogue systems and chatbots increasingly integrate into everyday interactions, the need for efficient and accurate evaluation methods becomes paramount. This study explores the comparative performance of human and AI assessments across a range of dialogue scenarios, focusing on seven key performance indicators (KPIs): Coherence, Innovation, Concreteness, Goal Contribution, Commonsense Contradiction, Incorrect Fact, and Redundancy. Utilizing the GPT-4o API, we generated a diverse dataset of conversations and conducted a two-part experimental analysis. In Experiment 1, we evaluated multi-party conversations on Coherence, Innovation, Concreteness, and Goal Contribution, revealing that GPT models align closely with human judgments. Notably, both human and AI evaluators exhibited a tendency towards binary judgment rather than linear scaling, highlighting a shared challenge in these assessments. Experiment 2 extended the work of Finch et al. (2023) by focusing on dyadic dialogues and assessing Commonsense Contradiction, Incorrect Fact, and Redundancy. The results indicate that while GPT-4o demonstrates strong performance in maintaining factual accuracy and commonsense reasoning, it still struggles with reducing redundancy and self-contradiction. Our findings underscore the potential of GPT models to closely replicate human evaluation in dialogue systems, while also pointing to areas for improvement. This research offers valuable insights for advancing the development and implementation of more refined dialogue evaluation methodologies, contributing to the evolution of more effective and human-like AI communication tools.
Although human evaluation remains the gold standard for open-domain dialogue evaluation, the growing popularity of automated evaluation using Large Language Models (LLMs) has also extended to dialogue. However, most frameworks leverage benchmarks that assess older chatbots on aspects such as fluency and relevance, which are not reflective of the challenges associated with contemporary models. In fact, a qualitative analysis on Soda, a GPT-3.5 generated dialogue dataset, suggests that current chatbots may exhibit several recurring issues related to coherence and commonsense knowledge, but generally produce highly fluent and relevant responses. Noting the aforementioned limitations, this paper introduces Soda-Eval, an annotated dataset based on Soda that covers over 120K turn-level assessments across 10K dialogues, where the annotations were generated by GPT-4. Using Soda-Eval as a benchmark, we then study the performance of several open-access instruction-tuned LLMs, finding that dialogue evaluation remains challenging. Fine-tuning these models improves performance over few-shot inferences, both in terms of correlation and explanation.
Despite being heralded as the new standard for dialogue evaluation, the closed-source nature of GPT-4 poses challenges for the community. Motivated by the need for lightweight, open source, and multilingual dialogue evaluators, this paper introduces GenResCoh (Generated Responses targeting Coherence). GenResCoh is a novel LLM generated dataset comprising over 130k negative and positive responses and accompanying explanations seeded from XDailyDialog and XPersona covering English, French, German, Italian, and Chinese. Leveraging GenResCoh, we propose ECoh (Evaluation of Coherence), a family of evaluators trained to assess response coherence across multiple languages. Experimental results demonstrate that ECoh achieves multilingual detection capabilities superior to the teacher model (GPT-3.5-Turbo) on GenResCoh, despite being based on a much smaller architecture. Furthermore, the explanations provided by ECoh closely align in terms of quality with those generated by the teacher model.
Large Language Models (LLMs) have showcased remarkable capabilities in various Natural Language Processing tasks. For automatic open-domain dialogue evaluation in particular, LLMs have been seamlessly integrated into evaluation frameworks, and together with human evaluation, compose the backbone of most evaluations. However, existing evaluation benchmarks often rely on outdated datasets and evaluate aspects like Fluency and Relevance, which fail to adequately capture the capabilities and limitations of state-of-the-art chatbot models. This paper critically examines current evaluation benchmarks, highlighting that the use of older response generators and quality aspects fail to accurately reflect modern chatbot capabilities. A small annotation experiment on a recent LLM-generated dataset (SODA) reveals that LLM evaluators such as GPT-4 struggle to detect actual deficiencies in dialogues generated by current LLM chatbots.
In task-oriented conversational AI evaluation, unsupervised methods poorly correlate with human judgments, and supervised approaches lack generalization. Recent advances in large language models (LLMs) show robust zeroshot and few-shot capabilities across NLP tasks. This paper explores using LLMs for automated dialogue quality evaluation, experimenting with various configurations on public and proprietary datasets. Manipulating factors such as model size, in-context examples, and selection techniques, we examine "chain-of-thought" (CoT) reasoning and label extraction procedures. Our results show that (1) larger models yield more accurate dialogue labels; (2) algorithmic selection of in-context examples outperforms random selection; (3) CoT reasoning where an LLM is asked to provide justifications before outputting final labels improves performance; and (4) fine-tuned LLMs outperform out-of-the-box ones. Our results indicate that LLMs that are suitably fine-tuned and have sufficient reasoning capabilities can be leveraged for automated dialogue evaluation.
This research investigates the effect of prompt design on dialogue evaluation using large language models (LLMs). While LLMs are increasingly used for scoring various inputs, creating effective prompts for dialogue evaluation remains challenging due to model sensitivity and subjectivity in dialogue assessments. Our study experimented with different prompt structures, altering the sequence of output instructions and including explanatory reasons. We found that the order of presenting reasons and scores significantly influences LLMs' scoring, with a "reason-first" approach yielding more comprehensive evaluations. This insight is crucial for enhancing the accuracy and consistency of LLM-based evaluations.
The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language Models (LLMs), existing approaches still struggle with the one-to-many problem, and exhibit subpar performance in domain-specific scenarios. We assume the commonsense reasoning biases within LLMs may hinder their performance in domainspecific evaluations. To address both issues, we propose a novel framework SLIDE (Small and Large Integrated for Dialogue Evaluation), that leverages both a small, specialised model (SLM), and LLMs for the evaluation of open domain dialogues. Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) a strategy for incorporating the evaluation results from both the SLM and LLMs. Our empirical results demonstrate that our approach achieves state-of-the-art performance in both the classification and evaluation tasks, and additionally the SLIDE evaluator exhibits better correlation with human judgements. Our code is available at https:// github.com/hegehongcha/SLIDE-ACL2024.
Automatic open-domain dialogue evaluation has attracted increasing attention. Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with a given context. However, adversarial negative responses, despite possessing high content similarity with the contexts, are semantically different. Consequently, existing evaluation metrics are not robust enough to evaluate such responses, resulting in low correlations with human judgments. While recent studies have demonstrated the effectiveness of Large Language Models (LLMs) for open-domain dialogue evaluation, they still face challenges in effectively handling adversarial negative examples. In this paper, we propose an effective framework for open-domain dialogue evaluation, which combines domain-specific language models (SLMs) enhanced with Abstract Meaning Representation (AMR) knowledge with LLMs. The SLMs can explicitly incorporate AMR graph information of the dialogue through a gating mechanism for enhanced dialogue semantic representation learning. Both the evaluation result from the SLMs and the AMR graph information are incorporated into the LLM's prompt for enhanced evaluation performance. Experimental results on open-domain dialogue evaluation tasks demonstrate the superiority of our method compared to a wide range of state-of-the-art baselines, especially in discriminating adversarial negative responses. Our code and data are publicly available at https://github.com/Bernard-Yang/SIMAMR.
Building a reliable and automated evaluation metric is a necessary but challenging problem for open-domain dialogue systems. Recent studies proposed evaluation metrics that assess generated responses by considering their relevance to previous dialogue histories. Although effective, these metrics evaluate individual responses directly rather than considering their relative quality compared to other responses. To handle this, we propose PairEval, a novel dialogue evaluation metric for assessing responses by comparing their quality against responses in different conversations. PairEval is built on top of open-sourced and moderate-size language models, and we make them specialized in pairwise comparison between dialogue responses. Extensive experiments on multiple benchmarks demonstrate that our metric exhibits a higher correlation with human judgments than baseline metrics. We also find that the proposed comparative metric is more robust in detecting common failures from open-domain dialogue systems, including repetition and speaker insensitivity.
In this paper, we introduce CodingTeachLLM, a large language model (LLM) designed for coding teaching. Specially, we aim to enhance the coding ability of LLM and lead it to better teaching mode in education context. Thus, we propose an end-to-end prior-based three-phases supervised fine-tuned model, which is proved more competitive than traditional fine-tuning method. More specifically, our model realizes the structural disassembly and incremental guided output of educational knowledge. To this end, we robustify data classification of three types via a sampler and overlap estimation neural network, and inject the preprocessing datasets into pre-trained model in three batches for LORA fine-tuning. Then, we design a prior module couples system prompt, vector databases, and abstract syntax tree task segmentation. Finally, the compression method and regularization constraint are applied to the prior-based fine-tuned model, followed by text filter at the output end to obtain incremental guided results. Our model represents the first research effort to truly embody the tutor role with the features of abundant educational knowledge, step-by-step incremental guided outputs and non-disclosure of answers. Extensive experiments report that our model also achieves state-of-the-art in code abilities compared to open-source models, reaching an impressive 75.10% on the HumanEval (@pass 1) benchmark. Additionally, our model maintains strong conversational capabilities, with the 13B quantized version achieving scores of 56.34, 50.60, and 45.27 respectively on the MMLU, C-Eval, and AGIEval (5 shot) dialogue evaluation benchmarks.
Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique, reference-free neural metrics that better align with human evaluations. Notably among them, large language models (LLMs), particularly the instruction-tuned variants like ChatGPT, are shown to be promising substitutes for human judges. Yet, existing works on utilizing LLMs for automatic dialogue evaluation are limited in their scope in terms of the number of meta-evaluation datasets, mode of evaluation, coverage of LLMs, etc. Hence, it remains inconclusive how effective these LLMs are. To this end, we conduct a comprehensive study on the application of LLMs for automatic dialogue evaluation. Specifically, we analyze the multi-dimensional evaluation capability of 30 recently emerged LLMs at both turn and dialogue levels, using a comprehensive set of 12 meta-evaluation datasets. Additionally, we probe the robustness of the LLMs in handling various adversarial perturbations at both turn and dialogue levels. Finally, we explore how model-level and dimension-level ensembles impact the evaluation performance. All resources are available at https://github.com/e0397123/comp-analysis.