cs.CL · 2026-07-15 · No. 54
Computation and Language, 2026-07-15.
13 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
13 entries-
01
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Hongru Cai, Yongqi Li, Ran Wei, Wenjie Li
cs.CL · cs.AI
Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most agent systems run on desktops or servers, which support tool use and task automation. Mobile devices are also important agent environments because they are widely accessible and contain users' data, sensors, and daily-use applications. Existing mobile...
-
02
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
Tapan Parikh
cs.CL · cs.AI · cs.CY
When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer every other model picks? Asked to "pick a word -- any word," 44 models chose "serendipity" 41% of the time. We characterize this convergence with a deliberately minimal instrument: 31 single-turn prompts, each naming a category with many valid one-word answers ("Name a tree."), asked four times per...
-
03
Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts
Jincheng Xie, Runheng Liu, Heyan Huang, Yawen Ling, Hanbin Dai, Yu Zheng, Wen Hu
cs.CL · cs.AI · cs.DC
Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns. Speculative decoding (SD) accelerates autoregressive generation by verifying multiple draft tokens in parallel, yet existing draft selection strategies primarily optimize acceptance likelihood. In large-scale MoE models, however, selecting draft tokens...
-
04
From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation
Mehak Dhaliwal, Rasta Tadayon, Andong Hua, Haewon Jeong, Yao Qin
cs.CL · cs.AI
LLMs can perform language-based quantitative prediction from unstructured inputs, but remain susceptible to hallucinations and overconfident errors, making it critical to know not only what a model predicts, but when its predictions can be trusted. We introduce CARE-PPO, a reinforcement learning framework that establishes a connection between loss prediction for uncertainty estimation and actor-critic PPO fine-tuning, enabling joint learning...
-
05
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
Minh Khoi Ho, Zihao Zhu, Runchuan Zhu, Levina Li, Zhiwen Fan, Zhangyang Wang, Junyuan Hong
cs.CL · cs.AI
As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical. While LLMs are trained to perceive and resonate with users' emotions, it remains unclear whether induced emotion can influence their sequential decision-making. We investigate this question using the Iowa Gambling Task (IGT), a classic psychological...
-
06
Language Identification with Succinct Machine-Independent Traces
Moses Charikar, Jon Kleinberg, Chirag Pabbaraju
cs.CL · cs.DS · cs.LG
Motivated by the power of large language models, there has been renewed interest in the Gold-Angluin model of language identification in the limit, with an eye toward variants of the model that might overcome the negative results for its original formulation. Recent papers on this question have proposed looking at computational traces and annotations of training strings as a source of additional power for a learner, reflecting empirical...
-
07
Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study)
Farnaz Farid, Raihan Alam, Al Al-Areqi, Farhad Ahamed, Muhammad Hassan Khan, Sadia Hossain, Irena Veljanova, Anika...
cs.CL · cs.AI · cs.CY · cs.ET · cs.HC
Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation. A prevalent challenge in mitigating this issue arises in non-English contexts and low socioeconomic classes, where limited data hinders the training of AI models for effective detection....
-
08
LakeQuest: A Three-Domain Benchmark for Grounded Question Answering across Data Lakes
Michael Solodko, Steven Gong, Guangwei Yu, Satya Krishna Gorti, Jesse C. Cresswell, Victor Zhong
cs.CL · cs.AI
While modern question answering (QA) systems excel on clean, schema-aligned corpora, real-world knowledge is rarely so neatly packaged. Answering questions over enterprise and scientific data lakes requires systems to navigate heterogeneous, weakly structured collections of tables, passages, and linked metadata. Current benchmarks abstract away this noisy discovery process, failing to evaluate end-to-end performance. To bridge this gap, we...
-
09
A Shared Subcircuit Lets LLMs Count Down Across Tasks
Jacob Dunefsky, Wes Gurnee, Emmanuel Ameisen
cs.CL · cs.LG
Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an ASCII table. These are all tasks that language models can do that requires tracking how many tokens remain before a target. In this work, we identify in Llama-3.1-70B-Instruct a general mechanism for performing these tasks: a "countdown subcircuit" that compares the current position to a goal length and estimates the time remaining until then....
-
10
Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals
Mohotarema Rashid, Lingzi Hong, Junhua Ding, K. S. M. Tozammel Hossain
cs.CL · cs.AI
Large language model (LLM) trading agents show promising performance in equity markets, yet remain narrowly focused on US equities with little evidence from live deployment. We present Fin-Analyst, a hybrid agent for FinMMEval 2026 Task 3: an eight-specialist LLM pipeline over news, SEC filings, fundamentals, analyst forecasts, technical indicators, and social sentiment, aggregated by a Meta-Agent for Tesla (TSLA), and a lightweight rule...
-
11
RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls
Brenda Lelis, Rodrigo Cabral-Carvalho
cs.CL · cs.AI · cs.MA
Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation problem: every token spent on coordination is unavailable to task instructions or evidence when a call is assembled under a fixed context budget. We introduce the Roundtable Context Window Test...
-
12
Fine-Tuned Multi-Agent Framework for Detecting OCEAN in Life Narratives
Rasiq Hussain, Darshil Italiya, Joshua Oltmanns, Mehak Gupta
cs.CL · cs.LG · cs.MA
Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, but pretraining of these models can induce latent "personality-like" biases, making single-model inferences inconsistent. We propose a fine-tuned multi-agent framework for detecting OCEAN...
-
13
Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing
Gabriel Paris-Colombo, Rodrigo M. Cabral-Carvalho, Felipe D. Toro-Hernández
cs.CL · cs.AI
Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three large language models (GPT-4o, Gemini-2.5-Pro, Claude-Sonnet-4.5) using verbal fluency data. By applying trajectory-based NLP metrics to the items generated by 82 human participants and LLM output across eight temperature settings, we quantified three complementary dimensions: entropy (step size...
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.