Detect, Explain, Escalate: Low-Carbon Dialogue Breakdown Management for LLM-Powered Agents

• URL: http://arxiv.org/abs/2504.18839v2
• Date: Thu, 05 Jun 2025 18:27:49 GMT
• Title: Detect, Explain, Escalate: Low-Carbon Dialogue Breakdown Management for LLM-Powered Agents
• Authors: Abdellah Ghassel, Xianzhi Li, Xiaodan Zhu,
• Abstract summary: Large Language Models (LLMs) are transforming numerous applications, but their susceptibility to conversational breakdowns remains a critical challenge undermining user trust.<n>This paper introduces a "Detect, Explain, Escalate" framework to manage dialogue breakdowns in LLM-powered agents, emphasizing low-carbon operation.
• Score: 30.13634341221476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models (LLMs) are transforming numerous applications, their susceptibility to conversational breakdowns remains a critical challenge undermining user trust. This paper introduces a "Detect, Explain, Escalate" framework to manage dialogue breakdowns in LLM-powered agents, emphasizing low-carbon operation. Our approach integrates two key strategies: (1) We fine-tune a compact 8B-parameter model, augmented with teacher-generated reasoning traces, which serves as an efficient real-time breakdown 'detector' and 'explainer'. This model demonstrates robust classification and calibration on English and Japanese dialogues, and generalizes well to the BETOLD dataset, improving accuracy by 7% over its baseline. (2) We systematically evaluate frontier LLMs using advanced prompting (few-shot, chain-of-thought, analogical reasoning) for high-fidelity breakdown assessment. These are integrated into an 'escalation' architecture where our efficient detector defers to larger models only when necessary, substantially reducing operational costs and energy consumption. Our fine-tuned model and prompting strategies establish new state-of-the-art results on dialogue breakdown detection benchmarks, outperforming specialized classifiers and significantly narrowing the performance gap to larger proprietary models. The proposed monitor-escalate pipeline reduces inference costs by 54%, offering a scalable, efficient, and more interpretable solution for robust conversational AI in high-impact domains. Code and models will be publicly released.

Related papers

• Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement [43.532921045069365]
  Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks.<n>Current techniques, such as static knowledge distillation, resource-intensive reinforcement learning from human feedback, or limited self-reflection to yield substantial and lasting performance gains.<n>We present a novel Reflect and Debate (D&R) framework that orchestrates multi-turn debates between smaller models and stronger teacher models, eliciting actionable feedback.
  arXiv  Detail & Related papers  (2025-06-04T03:52:20Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [0.0]
  Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents. Recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses. This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information [28.634126758365976]
  This paper presents Tox-chat, a Korean chemical toxicity information agent devised within these limitations.<n>We propose two key innovations: a context-efficient architecture that reduces token consumption through hierarchical section search, and a scenario-based dialogue generation methodology.
  arXiv  Detail & Related papers  (2025-03-22T12:34:15Z)
• Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings [9.763273544617176]
  Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning.<n>In this paper, we introduce a simple yet effective framework to address this challenge.<n>Our approach is specifically designed for per-utterance classification problems, which encompass tasks such as intent detection, dialogue state tracking, and more.
  arXiv  Detail & Related papers  (2025-03-07T17:46:13Z)
• Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models [53.580928907886324]
  Reasoning-Augmented Conversation is a novel multi-turn jailbreak framework. It reformulates harmful queries into benign reasoning tasks. We show that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios.
  arXiv  Detail & Related papers  (2025-02-16T09:27:44Z)
• Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production [6.459396785817196]
  This paper presents two novel approaches to enhance scalability and reduce latency in production dialogue systems. First, we introduce Symbol Tuning, which simplifies intent labels to reduce task complexity and improve performance in multi-turn dialogues. Second, we propose C-LARA, a framework that employs LLMs for data augmentation and pseudo-labeling to generate synthetic multi-turn dialogues.
  arXiv  Detail & Related papers  (2024-11-19T07:48:35Z)
• Intent Detection in the Age of LLMs [3.755082744150185]
  Intent detection is a critical component of task-oriented dialogue systems (TODS) Traditional approaches relied on computationally efficient supervised sentence transformer encoder models. The emergence of generative large language models (LLMs) with intrinsic world knowledge presents new opportunities to address these challenges.
  arXiv  Detail & Related papers  (2024-10-02T15:01:55Z)
• MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate [24.92465108034783]
  Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facilitated the use of these models as agents. We evaluate the behavior of a network of models collaborating through debate under the influence of an adversary.
  arXiv  Detail & Related papers  (2024-06-20T20:09:37Z)
• DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs [70.54226917774933]
  We propose the DecompositionAlignment-Reasoning Agent (DARA) framework. DARA effectively parses questions into formal queries through a dual mechanism. We show that DARA attains performance comparable to state-of-the-art enumerating-and-ranking-based methods for KGQA.
  arXiv  Detail & Related papers  (2024-06-11T09:09:37Z)
• On the Worst Prompt Performance of Large Language Models [93.13542053835542]
  Performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts. We introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries. Experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance.
  arXiv  Detail & Related papers  (2024-06-08T13:40:38Z)
• Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming [37.32997502058661]
  This paper introduces the textbfsentinel model as a plug-and-play prefix module designed to reconstruct the input prompt with just a few tokens. The sentinel model naturally overcomes the textit parameter inefficiency and textitlimited model accessibility for fine-tuning large target models. Our experiments across text-to-text and text-to-image demonstrate the effectiveness of our approach in mitigating toxic outputs.
  arXiv  Detail & Related papers  (2024-05-21T08:57:44Z)
• Multimodal Contextual Dialogue Breakdown Detection for Conversational AI Models [1.4199474167684119]
  We introduce a Multimodal Contextual Dialogue Breakdown (MultConDB) model. This model significantly outperforms other known best models by achieving an F1 of 69.27.
  arXiv  Detail & Related papers  (2024-04-11T23:09:18Z)
• DPP-Based Adversarial Prompt Searching for Lanugage Models [56.73828162194457]
  Auto-regressive Selective Replacement Ascent (ASRA) is a discrete optimization algorithm that selects prompts based on both quality and similarity with determinantal point process (DPP) Experimental results on six different pre-trained language models demonstrate the efficacy of ASRA for eliciting toxic content.
  arXiv  Detail & Related papers  (2024-03-01T05:28:06Z)
• Evaluating Language Model Agency through Negotiations [39.87262815823634]
  Negotiation games enable us to study multi-turn, and cross-model interactions, modulate complexity, and side-step accidental evaluation data leakage. We use our approach to test six widely used and publicly accessible LMs, evaluating performance and alignment in both self-play and cross-play settings.
  arXiv  Detail & Related papers  (2024-01-09T13:19:37Z)
• Fast and Accurate Factual Inconsistency Detection Over Long Documents [19.86348214462828]
  We introduce SCALE, a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy. This approach achieves state-of-the-art performance in factual inconsistency detection for diverse tasks and long inputs. We have released our code and data publicly to GitHub.
  arXiv  Detail & Related papers  (2023-10-19T22:55:39Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System [65.93577256431125]
  We propose an alternative approach called User-Guided Response Optimization (UGRO) to combine it with a smaller task-oriented dialogue model. This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models. Our approach outperforms previous state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2023-06-16T13:04:56Z)
• Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking [57.92608483099916]
  Large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. For more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial. We introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query.
  arXiv  Detail & Related papers  (2023-02-12T15:05:10Z)
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
  We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query. A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives. We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
  arXiv  Detail & Related papers  (2020-09-19T02:41:04Z)
• Low-Resource Knowledge-Grounded Dialogue Generation [74.09352261943913]
  We consider knowledge-grounded dialogue generation under a natural assumption that only limited training examples are available. We devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model. With only 1/8 training data, our model can achieve the state-of-the-art performance and generalize well on out-of-domain knowledge.
  arXiv  Detail & Related papers  (2020-02-24T16:20:32Z)
• Non-Autoregressive Dialog State Tracking [122.2328875457225]
  We propose a novel framework of Non-Autoregressive Dialog State Tracking (NADST) NADST can factor in potential dependencies among domains and slots to optimize the models towards better prediction of dialogue states as a complete set rather than separate slots. Our results show that our model achieves the state-of-the-art joint accuracy across all domains on the MultiWOZ 2.1 corpus.
  arXiv  Detail & Related papers  (2020-02-19T06:39:26Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.