{"total":19,"items":[{"citing_arxiv_id":"2606.26040","ref_index":105,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AI translation of literary texts is \"fine\", but readers still prefer human translations","primary_cat":"cs.CL","submitted_at":"2026-06-24T17:15:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Human readers prefer human literary translations over AI-generated ones for immersion and clarity despite finding MT adequate and struggling to identify the source.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21413","ref_index":26,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation","primary_cat":"cs.CL","submitted_at":"2026-06-19T13:28:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Compact 0.8B-7B models for bidirectional Japanese-English translation outperform large multilingual models on real-world domain benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18005","ref_index":270,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"LLM Consumer Behavior Theory: Foundations of a Novel Research Field","primary_cat":"cs.AI","submitted_at":"2026-06-16T14:51:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Introduces LLM Consumer Behavior Theory to analyze consumer behavior when LLMs serve as autonomous decision-making agents in markets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17255","ref_index":28,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task","primary_cat":"cs.CL","submitted_at":"2026-06-15T19:57:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A cascaded SimulST system using Parakeet and Qwen 3.5 with adaptive black-box policies and RAG context achieves +5.82 XCOMET-XL improvement on En→De for IWSLT 2026.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17234","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation","primary_cat":"cs.CL","submitted_at":"2026-06-15T19:27:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Empirical study finds verbalized per-token confidence methods in LLMs for MT perform similarly to internal signals on error detection and calibration but show little correlation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08011","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Rewrite to Translate, Translate to Reward: Reinforcement Learning for Source Rewriting in Machine Translation","primary_cat":"cs.CL","submitted_at":"2026-06-06T07:00:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RLSR trains source rewriters via RL with translation-quality improvement as the reward, outperforming prompt baselines at 4B scale while matching larger models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06177","ref_index":31,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios","primary_cat":"cs.CL","submitted_at":"2026-06-04T13:52:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Ouvia is a user-centered evaluation framework for speech translation usability in real-world scenarios, showing limited usability rates and the superiority of QA-based metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05924","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach","primary_cat":"cs.CL","submitted_at":"2026-06-04T09:27:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Multi-aspect iterative refinement with specialized LLMs generates superior literary translation data, enabling SFT and GRPO to produce LitMT-8B and LitMT-14B models scoring 67.25 and 69.07 CEA100 on MetaphorTrans, competitive with Claude Sonnet 4.5.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.04177","ref_index":153,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models","primary_cat":"cs.CL","submitted_at":"2026-06-02T19:46:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Lexical richness is a robust linguistic signal for AI-generated text detection across models and domains, while most other features are context-dependent.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22064","ref_index":84,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild","primary_cat":"cs.CL","submitted_at":"2026-05-21T07:00:06+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13596","ref_index":26,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Creativity Bias: How Machine Evaluation Struggles with Creativity in Literary Translations","primary_cat":"cs.CL","submitted_at":"2026-05-13T14:30:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Automatic evaluation tools for literary translations correlate poorly with expert human judgments on creativity and exhibit bias favoring machine-translated texts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13368","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation","primary_cat":"cs.CL","submitted_at":"2026-05-13T11:27:32+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Document-level machine translation followed by segment-level LLM refinement provides the strongest and most stable improvements in literary translation quality, mainly enhancing fluency and style rather than adequacy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12227","ref_index":78,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:04:18+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10714","ref_index":165,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish","primary_cat":"cs.CL","submitted_at":"2026-05-11T15:24:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Cross-lingual transfer and language-specific data efforts are interdependent and complementary for effective low-resource NLP, as demonstrated through Luxembourgish case studies and synthesis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09098","ref_index":29,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation","primary_cat":"cs.CL","submitted_at":"2026-05-09T18:12:10+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05003","ref_index":153,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Misaligned by Reward: Socially Undesirable Preferences in LLMs","primary_cat":"cs.CL","submitted_at":"2026-05-06T15:04:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Reward models for LLMs frequently select socially undesirable options across four social domains, show no overall best performer, and exhibit a bias-avoidance versus context-sensitivity trade-off.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04157","ref_index":237,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals","primary_cat":"cs.CL","submitted_at":"2026-05-05T18:00:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A feature-based decision tree with parsing-derived signals and heuristics detects LLM-generated code in a lightweight, CPU-only setup for SemEval-2026 Task 13.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.01017","ref_index":153,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Psychologically Potent, Computationally Invisible: LLMs Generate Social-Comparison-Eliciting Posts They Fail to Detect","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:28:10+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18758","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation","primary_cat":"cs.CL","submitted_at":"2026-04-20T19:07:32+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"erence translation 'as did also the other nobles who were attached to the Palace.' The transla- tion did capture some semantic elements such as 'great ones' in comparison to 'nobles' but by de- sign, BLEU would consider 0-precision, while BertScore would catch some quotient of similar- 15The metric signature is nrefs:405|case:mixed|eff: yes|tok:13a|smooth:floor[0.10]|version:2.5.1. 13 ity. Such patterns are more common in LLM based generation, compared to older controlled or limited vocabulary methods. B.2LEXparameters and grid search Our LEX component has multiple configurable pa- rameters, one controlling the target languages we include from dictionary and the rest for controlling the information added. Two parameters control the first-k entries that"}],"limit":50,"offset":0}