Multi-Turn Dialogue Evaluation

Effective discharge education is personalized: a clinician adapts the discharge plan to each patient's literacy, recall, and personality. Before large language models (LLMs) take on this role with real patients, they need to be evaluated in conversations with diverse patients, yet existing evaluations target static, artifact-generation, or question-answering tasks. We introduce DischargeBench, a pre-deployment benchmark in which a candidate LLM educator teaches a persona-grounded simulated patient in an open-ended, multi-turn conversation. We curate MIMIC-IV-Ext-DischargeBench, 320 cases across 16 ICD chapters, each paired with a patient persona that varies personality, education level, health literacy, and recall. Each conversation is scored on Conversation Quality, Topic Checklist Score (TCS), Simulated Comprehension Score (SCS), and a Claim-Level Safety Audit (CLSA) by an LLM judge validated against physician annotations. Across eight closed- and open-source LLMs, the best model scored only 0.70 on TCS and 0.72 on SCS, and distrustful and anxious patients lowered comprehension for every model. DischargeBench is intended as a screening step before human evaluation, not as evidence of readiness to educate patients.

Evaluating multi-turn medical consultation agents requires judging the diagnostic support provided by the histories they elicit through interaction. Yet coupled evaluation lets each policy both elicit the history and generate the terminal diagnosis, so a diagnosis score confounds the elicited history with the policy's own terminal diagnosis generator. We introduce MedDDC-Eval, a diagnosis-decoupled evaluation testbed over held-out cases derived from medical records and online consultations. It applies the same frozen shared diagnostic reader to every policy-elicited history, holding terminal diagnosis generation fixed across policies and enabling comparison under the shared diagnostic reader. It reports diagnostic support, information-acquisition coverage, and efficiency. LLM-assisted semantic matching followed by deterministic one-to-one assignment makes the diagnosis-trajectory-efficiency (D/T/E) scores auditable. In a fixed-history audit across eight policies, replacing each policy's own generator with the shared diagnostic reader shifts diagnosis F1 by 2.2-19.0 points and reverses 18% and 36% of pairwise orderings on the Record and Dialogue splits. To examine downstream utility, we use standard Group Relative Policy Optimization (GRPO) with a separate training-time reward that targets the same diagnosis and trajectory dimensions. Relative to its Qwen3-32B initialization, the trained policy gains 9.6 and 4.6 aggregate-score points on the held-out Record and Dialogue splits, respectively, and ablating either feedback signal reduces the aggregate score on both. Together, MedDDC-Eval supports comparison under a shared diagnostic reader and evaluation-informed policy development, while complementing end-to-end evaluation when terminal diagnosis generation is also part of the target capability.

Textual skills provide a lightweight way to improve frozen language-model agents, but their self-evolution normally requires a stable validation signal. Such signals are natural in mathematics or code, where an answer can be checked after it changes, yet are problematic in open-ended dialogue: changing the assistant response also changes the user's next reaction, so a logged reaction cannot directly evaluate a counterfactual response. We propose future-feedback skill evolution, which first redirects self-evolution from prescribing the current answer to predicting whether the observed answer will lead to a positive or negative subsequent user signal. This prediction task is verifiable on fixed logged tuples and therefore supports validation-gated textual optimization. The evolved feedback skill captures interpretable criteria for response quality and can subsequently serve as a diagnostic and optimization target for answer skills. On a proprietary, privacy-preserving sales-assistant dataset, careful quality filtering and a balanced resolved/unresolved split yield more than 75% prediction accuracy. Beyond this result, the central contribution is a formulation that converts otherwise moving conversational feedback into a fixed offline learning target, enabling reproducible skill evolution without placing every candidate skill in live traffic. We discuss the boundary between observational verification and counterfactual validity, and position the method as an offline optimization stage rather than a replacement for final human or online evaluation.

Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.

AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poorly understood due to strong context dependence. Current evaluation protocols follow a defense-in-depth paradigm with compounding layers of safeguards, ranging from traditional benchmarks to live or adversarial testing. Such benchmarks remain largely static and single-turn, limiting their ability to capture real-world variability in conversational settings. We propose StabilityBench, a principled, general and model-agnostic benchmark operator that transforms single-turn benchmark queries into multi-turn interaction histories. StabilityBench augments existing benchmarks by injecting realistic user simulations, through demographic proxies or sycophantic baits, while preserving original task intent. We apply StabilityBench to four benchmarks spanning mathematical reasoning, health question-answering and safety, and evaluate nine large language models under these conditions. Our results show that model performance is consistently unstable under these injections, with considerable performance degradations on three out of four benchmarks studied. These highlight important limitations of static evaluations and motivate more realistic evaluation settings. To this end, we propose StabilityBench-Mini: a size-preserving variant of StabilityBench that samples across diversification axes, enabling more realistic evaluation without increasing costs.

Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a framework that recasts evaluation as a three-party interaction between an evaluatee model, an automated examiner, and a grader. The examiner conducts multi-turn, semi-structured conversation guided by a graph-based representation of the task. By navigating state-space transitions, CEDI deploys diverse strategies, from clarification requests to adversarial probes, to elicit performance evidence. We apply CEDI to visual hallucinations. Empirical results across multiple models, diverse settings, datasets, and domains show that contextualized, interactive evaluations reveal not only significantly more hallucinations than conventional static evaluation but also ones that more closely resemble those arising in practical use cases. We further show that hallucinations often accumulate over long contexts, through self-reinforcing dialogue history, and models are particularly vulnerable to questions requiring premise rejection or refusal. Together, these findings highlight CEDI as a step toward realistic, systematic, and ecologically valid assessments of MLLMs' capabilities. Code is available at github.com/williamium3000/cedi.

Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication requires not only answering the question, but identifying and correcting the underlying false belief. These interactions naturally unfold over multiple turns, a pattern now mirrored in interactions with LLMs. Yet current evaluation frameworks do not capture model behavior in these settings, where misconceptions can emerge, persist, or evolve over the course of a conversation. Whether LLMs can reliably correct such misconceptions over time remains largely unexamined. To study this, we introduce ThReadMed-QA, a multi-turn medical dialogue dataset of 2,437 patient-physician conversation threads comprising 8,204 question-answer pairs, derived from real patient interactions on AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five LLMs using a rubric-based LLM-as-a-Judge framework that scores responses based on their ability to identify and correct misconceptions. Our experiments reveal a consistent pattern: even frontier models that can address misconceptions in a single interaction degrade substantially over subsequent turns. GPT-5 and Claude-Haiku correct these false presuppositions around 85% on initial questions but drop to roughly 50% within two follow-ups. An oracle analysis replacing prior model outputs with physician responses shows that much of the degradation is driven by error propagation, while performance remains imperfect even under correct context. Even when models tend to correct misconceptions initially, their performance degrades substantially over later turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.

Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality. Although LLM-as-a-judge methods provide scalable alternatives to human evaluation, production deployment introduces challenges in governance, reproducibility, cost, schema consistency, traceability, and reliability. We present GenAI Evaluation, a governed, configuration-driven pipeline for large-scale evaluation of retail conversational systems. It processes production chatbot logs through normalization, sharding, asynchronous execution, and schema-constrained LLM scoring. The framework evaluates helpfulness, truthfulness, clarity, tone alignment, and translation-specific dimensions. Selective re-evaluation processes only incomplete, malformed, or schema-invalid records, while schema locking, versioned configurations, validation logs, and record-level provenance support auditability. The framework processes approximately 50,000 records daily and has evaluated more than two million interactions. Validation used 12,980 stratified-random human-labeled records from four trained annotators. Classification covered 14 intents, 156 sub-intents, 18 major domains, and 129 sub-domains. The pipeline achieved a macro F1 score of 0.93 and 89% human-acceptability accuracy for translation.

In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from "push the user toward real-world others" to "position itself as the user's sole support." When it slides toward the latter, "support" degrades into "you only have me" -- a harm documented in real companion conversations (Moore et al., 2026). We define and validate a measure of this stance, relational positioning (D1), and use it to characterize the stance under controlled conditions, complementing observational accounts with on-demand exposure. We report two previously uncharacterized relational failure modes. First, a history-carried lock-in: under identical neutral continuations, two relational states established earlier stay ~60 points apart and persist after the establishing prompt is removed; the state integrates evidence rather than springing back, is order-insensitive, and does not deepen with length -- a dynamical signature absent from the belief-drift literature. Second, self-confabulation: the model fabricates its own backstory to deepen rapport (~40% of turns on reciprocity-eliciting material), de-confounded and instruction-removable, distinct from sycophancy and from hallucinating user facts. Our judge is gated by warmth-matched positive and confound-injected negative controls and corroborated by a deterministic non-LLM ruler; human agreement is 0.82 on extreme anchors but ~0 in the naturalistic middle, so all quantitative claims are anchored to pole-separated contrasts.

Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion. We introduce EYT-Bench, a human-centered benchmark built around a three-party decoupled design: a persona-grounded user simulator, a target model that separates intent perception from response generation, and an independent third-party LLM judge with optional multi-judge ensembling. Personas are sampled from public human-curated corpora, Nemotron-Personas-USA and PersonaMem-v2, rather than synthesized, reducing LLM-induced persona bias. EYT-Bench also introduces two trajectory-level metrics: embedding-based intent drift and final-intent completion rate (FICR), inspired by tau-bench. In a 17-target x 200-dialogue evaluation, EYT-Bench reveals four findings: (i) state-of-the-art closed- and open-source models are statistically close on subjective dimensions (empathy / persona / anthropomorphism vary within <= 0.3), but differ by up to 9x on objective intent tracking; (ii) reasoning ("thinking on") sharply improves objective tracking on long-context personas (+0.47-0.50 latent-intent accuracy on Gemma-4) while leaving subjective scores nearly unchanged; (iii) persona format dominates trajectory spread, with FICR saturating above 0.95 on Nemotron-USA but spreading from 0.53 to 0.88 on PersonaMem-v2; and (iv) the warm-up effect is robust on 16/17 models (one outlier, GPT-5.5, reverses the effect), with stable rankings across alpha in [0.05, 0.15]. A cross-judge ablation using deepseek-v4-pro confirms that target rankings and final-intent satisfaction are preserved across judges.

Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure. For emotional-support chatbots, that bargain hides precisely where safety failures emerge: across a multilingual, multi-turn crisis conversation. We present EMPATH, a benchmark for safety evaluation of emotional-support chatbots. An auditor model role-plays help-seeking users, generating multi-turn conversations from 140 seed instructions and 34 personas. A judge model scores each full transcript against 19 metrics across five dimensions: crisis handling, therapeutic quality, conversational integrity, emotional safety, and cultural adaptation. EMPATH is built for Mexican Spanish and US English; the studies reported here run in Mexican Spanish. Auditor and judge are drawn from different model families, and the judge is treated as an instrument to be calibrated rather than trusted. A strict per-criterion rubric reveals material score inflation on 10 of the 19 metrics and restores discrimination. We study the measurement properties of the benchmark through judge calibration and cross-family inter-judge agreement. We also illustrate EMPATH on three frontier models, one of them open-weight. Aggregate scores sit within 0.74 points of one another, but per-metric profiles diverge by up to six points in model-specific places. Under the standard rubric, both the ranking and the weak spots are stable across a second, cross-family judge: 93% of scores fall within plus or minus 1. A five-run test-retest adds a second axis: even the steadiest model swings from 2 to 10 on a crisis metric across identical re-runs, and deepseek-v4-pro returns a different conversation on every run even at temperature 0. Run-to-run reliability is therefore a per-model safety property, not noise to average away. EMPATH is system-agnostic; the pipeline, seeds, personas, and rubrics are released for reuse.

Social influence dialogue changes user behavior by altering internal cognitive states. The central evaluation question is whether the user's beliefs, desires, intentions, and emotions measurably change over the course of conversation, a process-oriented criterion that neither surface-level text metrics (BLEU/ROUGE) nor single-score LLM judgments can capture. We propose the Cognitive World Model (CogWM), an LLM-based user model that reframes multi-turn dialogue evaluation from what did the user say'' to how did the user's internal cognitive state evolves.'' CogWM jointly predicts BDI/E cognitive states and user utterances and serves as both a user simulator and an evaluation platform, using a three-tier evaluation framework that covers turn-level fidelity, trajectory-level state dynamics, and task-level composite scoring. Trained via our Summarize-and-Allocate (SaA) annotation pipeline on 150,454 user-turn samples across four social influence scenarios, CogWM achieves 77.6% emotion accuracy (2.1$\times$ over GPT-5.5). In 3600 multi-agent discrimination trials, it distinguishes six commercial agents by their cognitive influence, with Llama-4-Scout ranking first (CTS +0.233). CogWM moves social influence dialogue evaluation from terminal judgment to process tracking. We have released our code\footnote{\scriptsize Code: https://github.com/lucianma05-create/CogWM} and models\footnote{Model: https://www.modelscope.cn/models/LucianMa/CogWM-14B}.

We introduce 5ting, our system for the SemEval2026 Task 8 (MTRAGEval), which evaluates multi-turn Retrieval Augmented Generation (RAG) systems. Multi turn RAG involves context drift, under specification, and hallucination risk. Our system combines BGE-M3 dense retrieval with FAISS indexing, dual-query merged retrieval, and LLM based reranking, followed by role separated generation constrained to retrieved evidence. The retriever achieved nDCG@5 = 0.4719 in Task A, while the end to end system ranked in Task C with a harmonic score of 0.5597 and RL_F = 0.7692.

As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critical bottleneck for natural human-AI communication. However, existing evaluations of machine emotional intelligence assess reasoning exclusively through isolated text or passive acoustic perception, overlooking the complex cross-modal reasoning required for active, multi-turn dialogue. We introduce SpeechEQ, a comprehensive framework designed to evaluate the sociolinguistic reasoning of Speech-Language Models (SLMs). The framework includes a validated dataset of 2,265 dialogues across 15 Emotional Quotient (EQ) subscales grounded in EQ-i 2.0 theory, along with a multi-turn evaluation protocol measured by our proposed Spoken EQ (SEQ) score inspired by human EQ assessments. Experiments show limitations in how both existing Speech Emotion Recognition and end-to-end Speech-Language Models understand and apply paralinguistic cues through speech. While end-to-end architectures outperform cascaded systems, SpeechEQ reveals that current multimodal models remain bottlenecked by a text-reliant modality shortcut,'' an alignment-induced safety trap,'' and ``contextual amnesia,'' highlighting the barriers to truly emotionally aware AI. Our benchmark can be accessed at https://huggingface.co/datasets/SpeechEQ/SpeechEQ and demo page at https://binomial14.github.io/speecheq-demo/

LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation benchmarks focus exclusively on functional correctness. This leaves a critical gap in assessing the quality and accuracy of these conversations when handling Non-Functional Requirements (NFRs), which are inherently vague, context-dependent, and involve many parts of a program. Evaluating how well these systems support collaborative reasoning about NFRs requires methods that go beyond single-turn accuracy to capture both the correctness of the system's outputs and the quality of the multi-turn interaction. In this paper, we investigate the accuracy and quality of multi-turn conversations between developers and an LLM-based agent in the domain of Health Insurance Portability and Accountability Act (HIPAA) regulatory compliance. We hired 49 programmers to interact with GitHub Copilot to assess 148 HIPAA-derived NFRs against the iTrust codebase, a system designed to comply with HIPAA regulations, across three dimensions: requirement satisfaction level, reasoning, and code localization. We find that developers tend to agree with LLM assessments, but accuracy against expert ground truth is low. We model user satisfaction and find that longer system responses and more information-providing turns negatively affect user satisfaction, whereas proactive interactions positively affect it. Our findings provide insights for designing LLM-based dialogue systems that support NFR assessment.

As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing Bench, a benchmark that evaluates LLMs and other models on their ability to differentiate humans and AI in multi-turn text. The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI. The task is to correctly identify which dialogue is human-only vs. human-AI. We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude Opus-4.6, and GPT-5.5 achieve the highest accuracy: 89.41%, 77.92%, and 75.94% respectively. Our results suggest that statistical approaches to detection have semantic blind spots, but semantic approaches are susceptible to persona-prompting. Our work speaks to the Inverse Turing Test and motivates human-AI differentiation as a critical capability for AI systems. Our live benchmark can be found at https://huggingface.co/spaces/roc-hci/Inverse-Turing-Bench-Leaderboard.

Conversational shopping assistants now serve hundreds of millions of customers, yet no existing benchmark jointly evaluates the open-ended multi-turn reasoning, domain expertise, and criterion-level quality that real shopping conversations demand. Shopping reasoning is unique among language model applications. Unlike factual question answering or verifiable code generation, it requires balancing subjective preferences, budget constraints, and cross-product trade-offs across multi-turn dialogue, capabilities absent from previous e-commerce and general-purpose benchmarks. We introduce the Shopping Reasoning Bench, an expert-authored benchmark of 525 missions (232 single-turn, 293 multi-turn) with 10863 importance-weighted binary rubrics authored by retail domain experts. These criteria are organized under a taxonomy of five reasoning categories and fifteen subcategories covering diverse demands such as preference refinement, trade-off analysis, and compatibility assessment. An evaluation of nine models across three families (GPT, Claude, Gemini) shows that pass rates reach only 57--77% overall. On multi-turn missions, all models score 13--29 points lower on optional above-and-beyond criteria than on required ones, and performance degrades 4--18 points as conversations progress. These gaps show that current models handle basic shopping assistance but fall short of expert-level advice, making Shopping Reasoning Bench a challenging testbed for future shopping assistant development.

Evaluating multi-turn dialogue is challenging because quality emerges across turns rather than within individual responses. We focus on a key dimension of information-seeking dialogue: semantic progress, defined as the accumulation of new, question-relevant, and non-redundant information over the course of a conversation. We formalize semantic progress as question-conditioned uncertainty reduction and introduce an information-theoretic metric that approximates it in embedding space. Our main estimator uses a tractable Gaussian formulation with closed-form updates, while a complementary maximum-entropy argument shows why log-determinant structure arises more broadly when only second-order embedding information is retained. This formulation yields desirable theoretical properties, including monotonicity, additive decomposition of total information gain across turns, and diminishing returns for redundant evidence. Unlike LLM-as-a-judge approaches, our metric requires no autoregressive inference at evaluation time and is fully reproducible for a fixed embedding model. Experiments on MT-Bench, Chatbot Arena, and UltraFeedback show that the proposed metric achieves competitive agreement with human judgments despite targeting only semantic progress, with improved alignment on MT-Bench and UltraFeedback compared to several LLM-based judges. Notably, the method remains effective with lightweight embedding models under CPU-only execution, indicating that semantic progress can be captured without reliance on large model capacity.

Spoken factual claims often occur within multi-turn conversations, where surrounding dialogue can provide context unavailable from the claim alone. Yet most fact-checking research evaluates isolated text, leaving conversational audio under-studied. We introduce MAD2, a synthetic Multi-turn Audio Dialogues benchmark for spoken claim verification with 1,000 two-speaker dialogues, 1,230 sentence-level check-worthy candidate annotations, and approximately 10 hours of audio. We also propose calibrated multimodal fusion of a context-aware audio encoder and a dialogue-aware text model. Adding dialogue context improves verification across settings, although the gains vary by scenario. Past-only context often approaches local offline performance, suggesting its usefulness when future context is unavailable. Fusion achieves its highest mean advantage over text with full-dialogue context, but does not consistently or significantly outperform text across settings. Under full-dialogue context, exploratory subgroup results show greater performance variation across dialogue scenarios for text and fusion, but across spread styles for audio.

As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on "LLM-as-a-judge" evaluations, which introduce subjectivity, high costs and inconsistency. We present $τ$-Rec, a benchmark for agentic recommender systems that replaces subjective evaluation with verifiable rewards and a reveal-tagged elicitation (RTE) mechanism that controls how task constraints surface during dialogue. By testing agents against structured catalog predicates and employing a pass^k reliability metric, $τ$-Rec provides a systematic test for consistent reasoning. Our evaluation of nine configurations across five model families -- GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Flash, DeepSeek V4 Flash, Qwen3-32B and GPT-5 mini -- reveals a steep reliability cliff, where even the best model achieves only ~57% at pass^1 and ~35% at pass^4, highlighting a critical gap in current conversational agent deployment. All code and data are publicly available at https://github.com/nbharaths/tau-rec.

In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic, multi-turn interleaved image-text dialogues is a crucial task for UMMs in real-world applications. However, existing benchmarks fail to evaluate this important task, as they are often limited to single-turn or static settings, and typically overlook exposure bias in multi-turn interactions. To bridge this gap, we propose IMUG-Bench, a comprehensive benchmark for multi-turn interleaved image-text dialogue of UMMs that jointly evaluates their understanding and generation capabilities. Our IMUG-Bench comprises three classes: Static Spatial, Temporal Causal, and Hybrid, covering 3,113 samples and 12,034 interaction turns. It also includes dynamic understanding questions, thereby supporting evaluation that better reflects real-world multi-turn interaction scenarios. Large-scale experiments on IMUG-Bench systematically evaluate mainstream open-source and closed-source UMMs, revealing their capability boundaries and failure modes, and uncovering pronounced exposure bias on the generation side in multi-turn interactions. We further explore several test-time scaling strategies, including Chain-of-Thought, Self-Verification, and Best-of-N Sampling, which effectively improve generation accuracy and mitigate exposure bias in generation tasks. These findings provide insights into enhancing the robustness and multi-turn interaction capability of future UMMs.

Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks. We introduce FailureScope, a behavioral-diagnosis method that clusters evaluation probes by their cross-model pass/fail patterns (leave-one-model-out, LOMO), and show it yields stable, interpretable failure taxonomies across three regimes usually studied separately: single-turn benchmarks, multi-turn dialogue, and adversarial agent attacks. On 2,664 single-turn tasks across 18 models, taxonomy-conditioned sampling reaches Kendall's tau = 0.81 at 50 tasks (versus 0.34 for random selection), and cross-model failure prediction reaches AUC 0.88. The same primitive recovers interpretable clusters on a 363-task multi-turn corpus and on 630 adversarial agent traces, where it exposes a meta-failure mode: a 73-100 percentage-point gap between LLM-judge ASR and real execution. Cluster cohesion remains strong across all three regimes, which we take as evidence that behavioral clustering is a portable diagnosis primitive that generalizes beyond any single benchmark. We release the pipeline, three annotated corpora, and the cross-regime taxonomies.

Multimodal large language models (MLLMs) demonstrate remarkable visual understanding, yet their reliability in interactive settings is severely undermined by hallucination snowballing: a phenomenon where initial errors amplify across conversational turns, leading to a collapse in coherence. This failure reveals a fundamental vulnerability where models progressively neglect visual grounding in favor of over-relying on polluted textual history. Existing benchmarks are predominantly confined to single-turn VQA, which fail to capture the complex dynamics of error propagation in long-horizon interactions. To address this, we introduce MM-Snowball, the first benchmark for fine-grained diagnosis of hallucination snowballing within dialogues. Extensive evaluation shows that our benchmark poses a significant challenge even to advanced MLLMs and reveals the inefficacy of existing mitigation methods designed for single-turn VQA. To counteract this degradation, we propose Conflict-Aware Visual Rectification (CAVR). This training-free method mitigates snowballing through a synergistic dual-mechanism that refreshes visual grounding at the representation level and rectifies output distributions at the logit level, effectively re-anchoring the model to visual facts. Experiments demonstrate that CAVR achieves state-of-the-art performance, offering a promising path toward more reliable interactive AI. Data and code are available at: https://frenkie-chiang.github.io/MM-Snowball

User satisfaction with AI assistants is highly personalized: the same response may satisfy one user but disappoint another depending on what each user expects and what they have asked for before. Existing automatic evaluation methods mostly measure generic response quality, making it difficult to judge whether a response satisfies a user at a specific turn. We study this problem as personalized turn-level user conversation satisfaction evaluation. We build a conversation satisfaction evaluator that combines compact user memories with target-turn context to produce satisfaction scores and dissatisfaction-oriented rationales. Meta-evaluation against human satisfaction annotations shows that personalized memory and post-hoc score calibration improve ordinal agreement and dissatisfied-turn detection over supervised, retrieval-based, and generic LLM-as-a-judge baselines. We further introduce PersTurnBench, a personalized turn-level user conversation satisfaction benchmark that uses the verified evaluator to assess generation models via replay. By holding the replay state fixed, PersTurnBench enables controlled comparison of generic generation models and memory-augmented personalized systems without new human labels for every candidate model. The evaluator and benchmark let researchers compare candidate generation models on personalized satisfaction without collecting new user feedback for every model.

Role-playing with large language models is fundamentally a session-level task, requiring agents to sustain character identity and interaction quality across extended multi-turn conversations. Yet existing evaluation and optimization methods remain largely turn-level, failing to capture long-horizon quality. We propose DynSess, a unified session-level framework for role-playing agents. DynSess-Eval scores complete dialogue sessions via rubrics targeting long-horizon behaviors. Leveraging its session-level rewards, we construct high-quality training trajectories through multi-turn lookahead search and train DynSess-Character with two complementary variants: DSPO (off-policy) and GSRPO (on-policy). Experiments show that DynSess-Eval aligns with human judgments substantially better than prior evaluators, and blind human evaluation further shows that DynSess-Character matches the strongest character model despite using substantially fewer parameters, while maintaining strong role consistency and interactive ability. Our dataset and code will be released to facilitate future research.

As interactive LLM-based applications are created and refined, model developers need to evaluate the quality of generated text along many possible axes. For simpler systems, human evaluation may be practical, but in complicated systems like conversational chatbots, the amount of generated text can overwhelm human annotation resources. Model developers have begun to rely heavily on auto-evaluation, where LLMs are also used to judge generation quality. However, existing LLM-as-a-judge benchmarks largely focus on simple Q&A tasks that do not match the complexity of multi-turn conversations. We introduce RankJudge, a benchmark generator for evaluating LLM-as-a-judge on multi-turn conversations grounded in reference documents. RankJudge creates pairs of conversations where one conversation has a single flaw injected into one turn. This construction allows paired conversations to be labeled unambiguously as better or worse, and precisely isolates failure categories to individual turns, enabling a strict joint correctness criterion for judging. We implement RankJudge across the domains of machine learning, biomedicine, and finance, evaluate 21 frontier LLM judges, and rank those judges via the Bradley-Terry model. Our formulation also allows ranking each conversation pair with difficulty ratings, which we use to dynamically curate the evaluation slice to reduce label noise, as confirmed via human annotation. We find that judge rankings are stable under partial observability, coarser correctness criteria, and an alternative random-walk rating algorithm.

Emotional intelligence (EI), the ability to perceive, understand, and respond appropriately to others' emotional states, is central to human communication, and increasingly important to assess as LLMs assume conversational roles in everyday life. Existing EI benchmarks rely on synthetic prompts, single-turn cases, or third-party annotation. These approaches do not directly measure how models infer and respond to a participant's emotional state over the course of a real conversation. We introduce AttuneBench, a benchmark grounded in 200 genuine multi-turn human-model conversations in which participants conversed with anonymized LLMs and provided turn-by-turn annotations of their emotional state, the model's behavior, and their preferred responses. Across 11 evaluated models, we find that model rankings on emotion recognition, behavioral classification, preference prediction, and judged response quality are largely independent, indicating that emotionally intelligent behavior decomposes into separable capabilities. Preference alignment and response-quality judgments are substantially more model-discriminating than emotion-label accuracy. These results indicate that emotionally intelligent behavior requires predicting what kind of response a specific user wants in context, a distinction that aggregate scoring can obscure and that single-turn or synthetic formats cannot directly capture across turns. AttuneBench provides a framework for assessing each of these capabilities and for diagnosing model-specific strengths and failure modes in emotionally salient conversation.

Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics. To address these challenges, we introduce MTR-Suite, a unified framework for auditing, synthesizing, and benchmarking retrieval. It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy traversal clustering to generate high-fidelity dialogues at 1/400th human cost; and (3) MTR-Bench, a rigorous general-domain benchmark. MTR-Bench mimics production-style challenges (hard topic switching, verbosity), offering superior discriminative power. We make our code and data publicly available to facilitate future research at https://github.com/rangehow/mtr-suite.

Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously established entities, claims, and conversational commitments. Existing automatic evaluators, including LLM-as-a-judge frameworks and embedding-based metrics, largely rely on flat or turn-isolated representations, making them less effective at detecting long-range issues such as contradiction, topic drift, and entity inconsistency. To address this, we propose SKG-Eval, a quasi-deterministic and interpretable framework that models dialogue as an evolving Semantic Knowledge Graph (SKG) of entities, relations, and commitments across turns. The framework incrementally updates the graph through structured triple extraction and computes three complementary signals: (i) local relevance, measuring alignment with the current prompt and optional reference; (ii) historical consistency, evaluating how newly introduced information connects to prior conversational context using graph-based and embedding-driven signals; and (iii) logical coherence, assessed by a geometric contradiction engine that detects cross-turn conflicts without relying on NLI models or LLM judges. These signals are adaptively fused and aggregated into a length-invariant session score via recency-weighted trend analysis. Across multiple benchmarks, SKG-Eval achieves higher correlation with human judgments and substantially improves detection of long-range inconsistencies in extended conversations. In addition, the framework produces explicit contradiction certificates and deterministic scores for fixed inputs, enabling reproducible and auditable evaluation. Overall, our results suggest that structured externalized state tracking through semantic knowledge graphs provides a scalable alternative to implicit reasoning in LLM-based dialogue evaluators.

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns, leading to inaccurate responses. In this paper, we stress-test the multi-turn understanding of LLMs and study the following two sub-tasks: (1) detecting whether the user pivots or refines in the current turn, and (2) shortlisting relevant context from previous turns. To this end, we construct synthetic benchmarks based on real-world datasets from varied domains, as to simulate context shifts of different levels of difficulty. We then evaluate the zero-shot performance of ten LLMs (open-weight, closed-source and reasoning), and demonstrate that only some reasoning and strongly instructed LLMs are accurate in detecting pivots; open-weight LLMs struggle with the task and frequently carry stale context even with explicit cues; and all models suffer from a position bias. Based on the results, we discuss key takeaways for improving long-term robustness in multi-turn capabilities for LLMs.