The paper presents a system for AI contact centers that answers questions only from a closed set of verified QA units, returning the unit verbatim or routing to clarification, abstention, or handoff. The index is enriched offline using staged linguistic seeding (SLS), where human-authored slot recipes are expanded by GPT‑4.1‑mini and lightly filtered by humans, enabling a single retrieval pass without query-time generation. On held‑out data from two industrial domains, SLS improves hybrid retrieval recall at rank 1 to 0.881/0.930 and outperforms doc2query by 0.20/0.32, while also reducing unsupported content from 7‑13% to near 0%.
By Hyeonseop Yoon, Jeong-Eun Park
arXiv:2608.30023v1 Announce Type: cross
Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying...
By Dmitrij \.Zatuchin, Daniil Dzemesjuk
XTC (Exclude Top Choices) is a lightweight, head‑aware decoding operator that improves diversity in autoregressive language models by removing overly probable tokens that dominate the next‑token distribution. It works by identifying tokens above a plausibility threshold, probabilistically excluding the dominant choices, and renormalizing the remaining distribution. Across 60 experiments on models such as Gemma 3 and DeepSeek R1, XTC boosts Distinct‑2 scores by 11–15 % and cuts repeat trigrams by 27–47 %, while a Mechanical Turk study shows a 62.3 % preference for XTC‑generated text without loss of fluency.
By Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz-Ziv
arXiv:2607. 19794v1 Announce Type: cross Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count.
By Isabel Xu (The Overlake School), Cynthia Xu (The Overlake School), Rachel Ren (Edwards Vacuum Inc.), Cong Guo (The University of Memphis), Jiacheng Ding (The University of Memphis)
The study examines how 105 language models choose a single word from a large set of valid options, finding that 46% of the time they all pick the same word, "serendipity." Using 96 prompts that ask for one-word answers across various categories, the researchers measure convergence and each model’s share of the consensus. They observe that post‑training and persona‑tuned models diverge more, while heavily post‑trained assistants are more conformist, and that the field’s answer choices are more concentrated than human norms in most categories.
By Tapan Parikh
Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies overlook a common re...
CoHyDE is an iterative co‑training framework that jointly trains a dense encoder and an LLM rewriter for tool retrieval from large API catalogs. The encoder is fine‑tuned with InfoNCE on catalog‑style hypothetical descriptions generated by the rewriter, while the rewriter is preference‑aligned via DPO against the encoder’s retrieval scores. On a 10k‑tool subset of ToolBench, three rounds of CoHyDE outperform the best single‑component baseline by 2.5 pp NDCG@5 on standard queries and 6.3 pp on vague queries, with the largest gains on the hardest vague tier.
By Vaishali Senthil, Ashutosh Hathidara, Sebastian Schreiber
arXiv:2604. 26157v4 Announce Type: replace-cross Abstract: Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations.
By Zichao Wei
The study evaluates whether aggregated brand recommendation profiles can identify the language model that generated them. Using 6,475 responses from five deployed endpoints, a character‑n‑gram classifier accurately attributes single responses to the correct system (97.84% accuracy). However, when responses are aggregated into domain‑condition units, the classifier’s performance drops to 66.53%, and a forest model misclassifies all gift‑domain units, indicating that aggregated brand behaviour does not reliably reveal the underlying system.
By Dmitrij \.Zatuchin
arXiv:2608.23086v1 Announce Type: new
Abstract: Black-box large language models need confidence scores that can separate likely-correct from likely-incorrect outputs, enabling systems to prioritize h...
By Rounak Sharma, Ananya B. Sai, Soumyabrata Pal
arXiv:2607. 20537v1 Announce Type: cross Abstract: We introduce ReliableTableQA, a framework for training an LLM to annotate the statistical reliability of tabular QA results, not whether the query is answerable, but whether the computed answer is statistically meaningful.
By Huei-Chung Hu, Hsin-Tai Wu, Koyo Kobayashi
arXiv:2608. 11922v2 Announce Type: replace-cross Abstract: Predictive-distribution entropy is a strong answer-selection rule in retrieval-augmented generation (RAG) for question answering: across five QA benchmarks, selecting the answer a frozen respondent LLM produces with the lowest answer-token entropy lifts mean $F_1$ from 0.
By Hung-Chun Hsu, Po-Jen Ko, Che-Cheng Wu, Li-Yang Chang, Chuan-Ju Wang