arXiv Computation and Language By Faiz Ghifari Haznitrama, Alice Oh

Evaluating Communicative Success in Machine-Translated Conversation

Read the original on arXiv Computation and Language →

The paper introduces a three‑layer checklist-and-judge framework to evaluate interpreter agents that mediate live conversation across languages. It assesses semantic, pragmatic, and cultural‑social dimensions—naturalness, intent, and social appropriateness—rather than just fidelity, in both single‑turn and multi‑turn settings. Extensive validation shows that conventional MT metrics miss failures in stronger interpreters, and that context, structured instructions, and cultural cues influence communicative success.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Sep 2

WorldBench: Culturally Grounded Benchmark for Multilingual Agents

WorldBench is a new multilingual benchmark that tests large language model agents on culturally grounded everyday workflows, offering 1,600 tasks in seven languages and eight cultures. The benchmark evaluates agents through structured sandbox actions and introduces Constrained Task Success (CTS), a metric that assesses task completion, minimal modification, and other complementary aspects via deterministic and LLM-as-a-Judge evaluations. Experiments show that even leading models achieve only 49.2% CTS, revealing significant gaps in correctness and state preservation across languages and cultures.

By Leonardo Ranaldi, Sherrie Shen, Jushi Kai, Alexandra Birch
arXiv Computation and Language
Aug 28

Evaluating Language Models in Realistic Conversational Contexts

The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.

By Ilija Subasic, Andrew Rabinovich, Zhao Chen
arXiv AI
Jul 15

Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking

arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.

By Niranjan Kumar M, Balaji Nagarajan, Karthik Nair, Faysal Satter, Nithin Surendran