Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment

• URL: http://arxiv.org/abs/2607.17191v2
• Date: Wed, 22 Jul 2026 05:26:41 GMT
• Title: Toward Anthropomorphic Dialogue: A Closed-Loop Framework for Human-Like Chat Generation, Evaluation, and Preference Alignment
• Abstract summary: AnthroDial is a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment.<n>It combines a role-conditioned scheduled dialogue with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions.<n>We show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.
• Score: 11.379426404872833
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Benchmarking Speech-to-Speech Translation Models [55.00303727199927]
  Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol.<n>We introduce a benchmarking framework integrating 46 metrics across eight dimensions.<n>We deploy it on 1,248 model-language configurations from FLEURS and CVSS.
  arXiv  Detail & Related papers  (2026-06-02T07:01:33Z)
• SocialMemBench: Are AI Memory Systems Ready for Social Group Settings? [0.0]
  Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings.<n>Existing memory benchmarks evaluate dyadic or workplace dialogue; none targets multi-party social groups.<n>We introduce SocialMemBench, a benchmark of human-verified synthetic social group networks.
  arXiv  Detail & Related papers  (2026-05-18T03:11:48Z)
• The Autocorrelation Blind Spot: Why 42% of Turn-Level Findings in LLM Conversation Analysis May Be Spurious [35.76482964927589]
  We characterize the autocorrelation structure of 66 turn-level metrics across 202 multi-turn conversations.<n>We show that 42% of associations that appear significant under standard pooled testing fail to survive cluster-robust correction.<n>We present a two-stage correction framework combining Chelton (1983) effective degrees of freedom with conversation-level block bootstraps.
  arXiv  Detail & Related papers  (2026-04-15T20:54:39Z)
• Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation [86.62036852878354]
  Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding.<n>We propose RoPE-Perturbed Self-Distillation, a training regularizer that improves positional robustness.<n> Experiments on long-context adaptation of Llama-3-8B and Qwen-3-4B demonstrate consistent gains on long-context benchmarks.
  arXiv  Detail & Related papers  (2026-04-15T18:46:35Z)
• The Evaluation Blind Spot: A Stereological Theory of Benchmark Coverage for Large Language Models [0.0]
  Empirically, three independent leaderboards (Open LLM v2, an extended 12-benchmark suite, LiveBench) all have d_eff in [2.86, 4.80] on their competitive frontier.<n>A submodular greedy algorithm with the Nemhauser (1 - 1/e) guarantee finds a stable core of 4 benchmarks.<n>A counterfactual validation across 12 internal benchmarks and 27 categories confirms that the eigenstructure predicts which evaluations are irreplaceable.
  arXiv  Detail & Related papers  (2026-04-15T08:56:58Z)
• Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents [0.4666493857924357]
  We study whether inference-time scaffolding alone, without any additional training compute, can improve the performance of a small model in complex multi-step environments.<n>We evaluate Qwen3-8B on the AppWorld benchmark under both full-precision and 4-bit quantized configurations.<n>On full-precision inference, our scaffolded 8B model surpasses DeepSeek-Coder 33B Instruct (7.1%) from the original AppWorld evaluation.
  arXiv  Detail & Related papers  (2026-04-13T13:40:33Z)
• HuggingR$^{4}$: A Progressive Reasoning Framework for Discovering Optimal Model Companions [50.61510609116118]
  HuggingR$4$ is a novel framework that combines Reasoning, Retrieval, Refinement, and Reflection to efficiently select models.<n>It attains a workability rate of 92.03% and a reasonability rate of 82.46%, surpassing existing method by 26.51% and 33.25% respectively.
  arXiv  Detail & Related papers  (2025-11-24T03:13:45Z)
• One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework [51.50565654314582]
  Large language models can follow users' instructions throughout a dialogue spanning multiple topics.<n>Existing benchmarks are often limited to a fixed number of turns, making them susceptible to saturation and failing to account for the user's interactive experience.<n>We propose a framework for assessing multi-turn instruction-following ability.
  arXiv  Detail & Related papers  (2025-11-05T14:39:59Z)
• Navigating the Synchrony-Stability Frontier in Adaptive Chatbots [0.0]
  We present a computational evaluation framework that makes the core design tension explicit.<n>We simulate and compare explicit adaptation policies on a human-log dataset.<n>We find bounded policies achieve substantial gains in stability at a modest cost to synchrony.<n>We quantify "prompt legibility," showing that frontier policies reduce instruction churn and cut jarring register flips.
  arXiv  Detail & Related papers  (2025-09-30T22:50:30Z)
• Learning Adaptive Parallel Reasoning with Language Models [70.1745752819628]
  We propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end.<n> APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.<n>A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures.
  arXiv  Detail & Related papers  (2025-04-21T22:29:02Z)
• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers [92.5628632009802]
  We propose controllable counterfactuals (CoCo) to bridge the gap and evaluate dialogue state tracking (DST) models on novel scenarios. CoCo generates novel conversation scenarios in two steps: (i) counterfactual goal generation at turn-level by dropping and adding slots followed by replacing slot values, and (ii) counterfactual conversation generation that is conditioned on (i) and consistent with the dialogue flow. Human evaluations show that COCO-generated conversations perfectly reflect the underlying user goal with more than 95% accuracy and are as human-like as the original conversations.
  arXiv  Detail & Related papers  (2020-10-24T09:39:35Z)

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.