cs.CL · 2026-08-10 · No. 80
Computation and Language, 2026-08-10.
15 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
15 entries-
01
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
Ananya Sahu, Mohit Bansal, Elias Stengel-Eskin
cs.CL · cs.AI
While post-training improves the capabilities of large language models (LLMs), it generally lowers their output diversity and creativity, negatively impacting tasks that explicitly require creativity (e.g., story generation) as well as those that require it implicitly, e.g., reinforcement learning (RL). We instead propose CreativeInstruct, a scalable instruction-tuning method that teaches LLMs to balance creative, base-model-like generations...
-
02
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
Gyuwan Kim, Cheoneum Park, Tao Yang
cs.CL · cs.AI · cs.IR · cs.LG
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse...
-
03
Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding
Karim Radouane, Jose G Moreno, Lynda Tamine
cs.CL · cs.AI · cs.IR · cs.LG
Understanding concepts is fundamental to generalization. Despite their impressive performance on a wide range of tasks, Large Language Models (LLMs) still struggle with genuine concept understanding. Prior work has evaluated conceptual understanding in LLMs using natural-language benchmarks or narrowly scoped synthetic tasks, but these settings often conflate multiple skills or lack precise control over the underlying concepts and their...
-
04
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
Ruijie Hou, Yueyang Jiao, Zhao Wang, Yingming Li
cs.CL · cs.AI
Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized. \textbf{Contamination mitigation evaluation} intervenes in the decoding process to suppress memorization and restore a contaminated model's genuine capability, but its prevailing metric, the \textbf{G-AP} (\textbf{G}ap of \textbf{A}ggregate \textbf{P}erformance), is flawed. Discrete correct/incorrect readouts cannot...
-
05
Natural Language Processing Psychometrics
Edoardo Sebastiano De Duro, Emma Franchino, Massimo Stella
cs.CL · cs.AI · cs.SI
Natural Language Processing (NLP) models predicting mental health outcomes rarely specify what they measure: contextual knowledge, emotional content, or syntactic structure. NLP Psychometrics treats psychological prediction from text as a psychometric problem, linking scores to interpretable linguistic evidence and testing beyond the training text format. Nine LLMs, conditioned on controlled personas (cognitive digital shadows), completed...
-
06
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
Luc Hazenoot, Zhaochun Ren, Amirhossein Zohrehvand
cs.CL · cs.AI · cs.LG · econ.GN
Existing measures of how much a text is about a concept read the surface of the text: dictionary word shares, topic proportions, embedding similarities. They score the words a text uses, not the judgment a reader forms about it. Recent work has shown that a gap exists in what Large Language Models (LLMs) know internally versus what they express in their response. This paper asks whether that internal knowledge, read by monitoring the...
-
07
An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation
Emma Jouffroy, Warren Jouanneau, Marc Palyart
cs.CL · cs.AI
Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching. To address this, we propose a hybrid knowledge graph generation pipeline that grounds a Large Language Model (LLM) in the Wikidata multilingual Knowledge Graph (KG) while employing an agentic reflexion pattern to synthesize emerging concepts...
-
08
GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base
Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski
cs.CL · cs.AI · cs.DB
We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM). GPTKB 2.0 contains 38.4M triples over 1.6M canonical entities, together with 207.6K consolidated relations and 66K consolidated classes. Unlike prior LLM-derived knowledge bases that largely identify entities by surface strings, GPTKB 2.0 performs context-guided disambiguation during recursive KB construction,...
-
09
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
Bo Tang, Jianan Yang, Junyi Zhu, Yiquan Wu, Rui Zhao, Zhengyu Yang, Yang Zhang, Feiyu Xiong, Zhiyu Li, Jiajun Shen
cs.CL · cs.AI
Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically static profiles that cannot be updated locally without destabilizing unchanged traits, and benchmarks mainly test persona preservation and memory recall rather than whether a model speaks from a character's currently evolved state. We address both. PHASE-Tree is a...
-
10
Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression
Alex Kwon
cs.CL · cs.AI · cs.LG
Agent memory systems compress what they store, and compression is built to drop qualifiers, so a claim's epistemic standing tends not to survive being written to memory. We ask what governs whether it does. Matched notes carry the identical claim and identical stance and differ only in where that stance sits; one model compresses both under the same budget among the same filler notes, and a blind reader that never sees the condition scores...
-
11
Ask-E: An Environment for Calibrated Question Generation
Sarah Pratt, Jae Sung Park, Scott Geng, Ali Farhadi
cs.CL · cs.AI
Today, we improve models by training and evaluating them on problems at the frontier of their abilities. Creating such problems is itself a demanding task, requiring the ability to probe model limits and generalize beyond existing question distributions. It also means placing problems at a precise difficulty level, which requires understanding what it takes to solve them. In short, generating problems calibrated to a model's current frontier...
-
12
Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests
Seitaro Ono, Senna Ross, Jun Saiki
cs.CL · cs.AI · cs.CY · cs.LG
We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT). WEAT is a bias measurement method widely used in both computational social science and AI fairness research. It relies on cosine similarity as a measure of semantic association, which assumes that the embedding space is approximately isotropic. However, prior work has reported that many widely used...
-
13
Georeferencing Non-Gazetteered Place Names using Biological Specimen Records
Aneesha Fernando, Surangika Ranathunga, Kristin Stock, Raj Prasanna, Christopher B. Jones
cs.CL · cs.AI · cs.IR
Biological specimen records collected by natural history institutions constitute a rich source of temporal geographic knowledge, capturing biodiversity information about regional landscapes as they were recorded at different times. Using digitised data from the Allan Herbarium (New Zealand), this study identifies place names in these specimen locality descriptions that are absent from current gazetteers; we refer to these as non-gazetteer...
-
14
Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry
Yehan Yang, Junyuan Shang, Yang Li, Guanqun Zhao, Shuohuan Wang, Dianhai Yu
cs.CL · cs.AI
Long-context LLM inference is bottlenecked by quadratic attention computation and growing KV-cache costs. Existing sparse attention and KV-compression methods typically decide which tokens or heads to preserve from runtime attention scores, observation windows, calibration prompts, or learned gates, making head diagnosis input-dependent and costly to deploy. We propose Autonomy-of-Heads (AoH), a data-free method that identifies retrieval and...
-
15
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
Quanquan Li, Hongbo Zhang, Yihe Chi, Jingyu Li, Xidong Xi, Liuyang Song, Hongzhen Zhang, Yuxiang Huang, Jing Ke,...
cs.CL · cs.AI
Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge. Existing methods either use LLM-generated intervention tokens or rank candidates with the LLM's next-token probabilities. Both rely on the LLM's local preference, even though an LLM-selected token may be difficult for the SLM to build on. We present FutureBridge, which ranks joint LLM-SLM token candidates...
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.