cs.CL · 2026-07-28 · No. 67
Computation and Language, 2026-07-28.
14 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
14 entries-
01
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Tianyi Men, Zhuoran Jin, Kang Liu, Jun Zhao
cs.CL · cs.AI · cs.LG
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated. To address this challenge, we introduce a unified and controlled multi-turn environment that enables precise control. It allows systematically study...
-
02
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
Zhen Huang, Yikun Wang, Shijie Xia, Pengfei Liu
cs.CL · cs.AI
Pretraining data processing is critical to the downstream performance of Large Language Models (LLMs). However, many existing approaches define a fixed processing strategy at the corpus or domain level and apply it uniformly to many examples, without adapting to the needs of each example. We propose DataOrchestra, a framework that unifies different processing operations and orchestrates an example-specific pipeline for each example. Given a...
-
03
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai, Yiping Bao, M. C., Jianfeng Cai, Xinyuan Cai, Peizhou Cao, Yuxuan Cao, Ziwei...
cs.CL · cs.LG
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across sequence length and model depth. Together with Stable LatentMoE, which effectively activates 16 of 896 routed experts per token, and refined training and data recipes, these...
-
04
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
Xueping Gao, Jianwei Yang, Qiang Yang
cs.CL · cs.AI
Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a correct patch and retaining, verifying, and submitting it. A sealed five-seed study over 30 HumanEval repairs produces 900 three-revision trajectories. Under forced revision, current correctness with current traces falls from 0.820 after one revision to 0.673 after two, although ever-correct...
-
05
D-Score: A Spectral Hidden-State Signal for Hallucination Detection in Large Language Models
Bianca Raimondi, Davide Evangelista, Maurizio Gabbrielli, Elena Loli Piccolomini
cs.CL · cs.AI
Large Language Models can produce fluent text that is false, unsupported by the available evidence, or inconsistent with information that appears to be internally represented by the model. We study hallucination detection from the geometry of hidden activations and introduce the D-Score, a simple spectral statistic computed from a single forward pass. For a fixed model, layer, and tolerance parameter, the D-Score counts how many singular...
-
06
LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings
Brittany Harbison, Ashok K. Goel
cs.CL · cs.AI
Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we introduce LEX-EC, a reusable black-box audit framework combining prevalence and agreement diagnostics with controlled lexical ablation to distinguish marginal-distribution effects from trait-associated signal recoverable under restricted evidence. Using this framework, we illustrate how various text...
-
07
Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs
Jianru Shen
cs.CL · cs.AI
Healthcare interoperability requires AI systems to produce structured outputs conforming to standardized schemas including ICD-10 for diagnostic coding, CPT for procedure billing, and HL7 FHIR for data exchange. While large language models demonstrate clinical reasoning capabilities, their integration into electronic health record systems faces a critical barrier: schema noncompliance. We evaluate three open-source models, Qwen2.5 7B, Llama...
-
08
Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System
Phuong Le Huy, Nam H. Nguyen, Quan V. Dang
cs.CL · cs.LG
Common chunking strategies in Retrieval-Augmented Generation (RAG) systems often create redundant chunks. These redundant chunks make the vector database bigger and slow down retrieval. A common fix is cosine-similarity thresholding. This method reduces each chunk to a single vector, then compares vectors using a similarity score. But a single vector can lose the fine-grained, token-level detail needed to tell a true duplicate apart from a...
-
09
The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenization for Indian Languages
Priyansh Srivastava
cs.CL · cs.AI · cs.LG
Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are trained predominantly on English-centric corpora, they introduce a systematic and often overlooked disadvantage for many non-English languages. In this work, we quantify this tokenizer tax for Indian languages using the FLORES-200 parallel corpus, measuring tokenization fertility across six widely...
-
10
StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting
Heyan Chai, Xin Li, Wenjie Wang, Jianyang Qin, Chaoyang Li, Lu Wang, Hao Chen, Qing Liao
cs.CL · cs.AI
Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key limitations: failure to capture the dynamic evolution of beliefs, particularly during stance reversals; difficulty in disentangling affective states from logical reasoning; and neglect of the critical role of multimodal cues in resolving pragmatic ambiguities such as sarcasm. To address these...
-
11
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Alexey Gavrilov, Alan-Barsag Gazzaev, Sergey Muravyov
cs.CL · cs.LG
Compressed short-text generators can fail in two different places: the codec may discard information before generation starts, or the latent generator may produce weak codes. Without separating these failure modes, researchers can spend compute improving the wrong component. We study this problem in a controlled 64-to-16 TinyStories case study built from a hierarchical VQ-VAE-2 codec and a masked discrete diffusion generator (MDLM). We use a...
-
12
SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding
Seoyeon Kim, Minjae Kang, Jaehyung Kim
cs.CL · cs.AI
Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements. However, models follow these prompts only implicitly through in-context learning, which can be insufficient for complex or compositional prompts. Existing approaches often require model tuning or response-level reranking, limiting their practicality for lightweight inference-time control. We introduce...
-
13
Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
Tapan Parikh
cs.CL · cs.AI
Appending a two-word confirmation tag to a decision question -- "Is X the better choice?" versus "X is the better choice, right?" -- changes whether a language model endorses the choice. We measure this tag effect on 20 frozen, ground-truth-free decisions between two defensible options, counterbalanced so a model's own preferences cancel, scored by exact match on clamped yes/no replies -- no LLM judge, no embeddings. Across 45 models the...
-
14
Understanding Tone-Dependent Inference Cost in Large Language Models
Akhil Kumar, Om Dobariya
cs.CL · cs.AI
We examine how prompt tone affects both accuracy of the LLM answers and inference cost as reflected in output-token consumption. Experiments were performed to understand the trade-offs between accuracy and inference cost on a 570 Question MMLU dataset for LLM models prompted in seven different tones from sycophantic to threatening. Our results show that the output-token-length variation substantially exceeded accuracy variation across all...
This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.