cs.CL · 2026-07-30 · No. 69
Computation and Language, 2026-07-30.
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
APEX-Accounting
Julien Benchek, Austin Bennett, Jasmin Kern, Ryan Stevens, Rene Sultan, Charis Ching, Hayley Popiel, Vaibhav Mittal,...
cs.CL · cs.AI · cs.HC
We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved...
-
02
Same Evidence, Different Target: Decoding How Diagnostic Evidence Bears on Causal Questions from Language-Model States
Weiyi Kong, Zhuoran Li
cs.CL · cs.LG
The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes, estimands, pathways, or identifying assumptions. When the evidence and target vary together, a correct answer may reflect favorable or adverse wording, lexical overlap, or a familiar diagnostic pattern rather than matching the evidence to the causal question. We introduce paired prompts that...
-
03
From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs
Ruikang Zhang, Shuo Wang, Qi Su
cs.CL · cs.AI
Human personality theories characterize traits not as isolated attributes captured by a single score, but as stable individual tendencies expressed through the interplay among persons, situations, and behaviors. Existing studies of personality-related behavior in LLMs have primarily focused on outputs elicited under personality conditioning, characterizing observable trait-related expressions while lacking mechanistic evidence for the...
-
04
Metis: Memory Foundation Model
Zeyu Zhang, Ziliang Guo, Yihang Sun, Xichong Zhang, Xixuan Hao, Zehao Lin, Yang Zhang, Xiaoyan Zhao, Tong Shen, Bo...
cs.CL · cs.LG
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is still primarily implemented through external modules, leaving the native memory capability largely unexplored. In this paper, we take a first step toward this direction by introducing memory foundation models, which empower...
-
05
Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text
Lucas Zamora Vera, Jose A. Gonzalez-Lopez
cs.CL · cs.AI · eess.SP
State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain underexplored: whether selective state-space models (Mamba) improve on recurrent decoders, and how the output target (phonetic vs.\ character) interacts with that choice. On the public Brain-to-Text '25 benchmark, we study a controlled 2x2 grid (GRU vs.\ hybrid Mamba decoder; phonetic vs.\ character...
-
06
Automated Multilabel Mpox Research Classification with Explainable Transformer Models
Tanjim Taharat Aurpa
cs.CL · cs.AI
The Mpox outbreak remains a serious public health issue, with the WHO (World Health Organization) reporting increasing cases in some regions. Research on Mpox is vital for several reasons, including vaccine development, diagnostic improvement, viral evolution studies, and preventing future outbreaks. However, the large amount of research being published makes it difficult to organize and analyze information efficiently. This study focuses on...
-
07
Constitutional Midtraining: Content Presence Drives Alignment Gains
Desiree Cho, Cameron Tice, Bernie Hogan, Hunar Batra, Puria Radmard, Jun Zhao, Nigel Shadbolt
cs.CL · cs.AI · cs.CY · cs.LG
Post-training alignment is often shallow, eroding under fine-tuning. Whether midtraining interventions, cleanly isolated from post-training, can produce durable alignment remains untested. We test this via constitutional midtraining: inserting principled, values-based content into midtraining against a replay-only control at 120B scale. Our 394M-token constitutional corpus, built from Anthropic's Constitution, uses a 2x2 factorial design...
-
08
Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
Sizhe Zhou, Sheldon Yu, Hui Wei, Junda Wu, Siru Ouyang, Yizhu Jiao, Shijia Pan, Julian McAuley, Yu Zhang, Tong Yu, Jiawei Han
cs.CL · cs.AI
Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools. Yet research has largely passed over this medium: prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested: that an agent can keep a growing store organized as memories...
-
09
ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
Ruxi Gu, Zhenliang Zhang, Wei Wang
cs.CL · cs.AI
Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification. In...
-
10
Mergeable Model-Side Aggregation States for Long-Context Language Models
Dachuan Song, Junyu Yin, Zechen Hu, Xuan Wang
cs.CL · cs.AI
A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length grows. Examples include cardinality estimation, set relationships, and grouped statistics, which widely exist in logs, program outputs, tables, and multi-turn conversations. To provide the aggregation state required by these tasks, we introduce a model-side aggregation interface that...
-
11
Voice Memory for Agentic Speech Recognition
Chao-Han Huck Yang, Zih-Ching Chen, Piotr Zelasko, Zhehuai Chen, Jagadeesh Balam, Boris Ginsburg
cs.CL · cs.AI · cs.SD · eess.AS
We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory.md and decides per utterance whether to act on the hypothesis or abstain and keep the 1-best. Asynchronously, a score-gated optimizer revises that file through bounded edits, accepting an edit only when it strictly improves a held-out score. Extended from classical ASR-LM framework, we refer this...
-
12
Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification
Linyu Li, Zhi Jin, Yichi Zhang, Dongming Jin, Yuanpeng He, Huanyao Zhang, Xuan Zhang, Gadeng Luosang, Nyima Tashi
cs.CL · cs.LG · q-bio.QM
Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse first level right, yet once asked for a complete EC number their accuracy at levels two through four drops to almost zero, while specialized models and tools stay usable. We propose EC-Reason-Bench, a training-free, diagnostic evaluation protocol built to answer two...
-
13
Misalignment Has a Personality: A Big Five Account of Emergent Misalignment
Hasibur Rahman, Smit Desai
cs.CL · cs.AI
Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment through a mechanism that remains debated. We provide an interpretable account: in the models and corpora we study, misalignment behaves like a shift in personality. Prior work extracts activation directions for character traits from a single binary contrast, which can separate or steer behavior...
-
14
Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text
Aman Kumar, Lasitha Vidyaratne, Dipanjan D Ghosh, Arnab Chakrabarti, Ahmed K Farahat
cs.CL · cs.AI
Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways. Detecting a conflict is only the first step: review workflows may also need to determine its type, since numerical, temporal, referential, factual, and normative inconsistencies require different evidence and downstream checks. We study this problem as fine-grained...
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.