cs.CL · 2026-09-25 · No. 124
Computation and Language, 2026-09-25.
26 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
26 entries-
01
Agentic Detection of Online Conspiracies
Lior Biton, Oren Tsur
cs.CL · cs.LG
Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the speaker's intent -- the utterance's illocutionary force. We argue that this can be achieved through the use of relevant social...
-
02
Do Audio Language Models Hear and Read Distinctive Features Alike?
Yuanhao Chen, Peter Chin
cs.CL · cs.LG · cs.SD · stat.AP
Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members' mean representations. Averaging those offsets gives a direction for each stream, and we measure the cosine between the two. Because the two streams...
-
03
Does a model's stated reason for rejecting a candidate do any work?
Archit Rastogi
cs.CL · cs.AI · cs.LG
Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no date of death. That sentence is a claim about the text in front of the model, and it can be tested without any judge. We insert a real corpus sentence stating the named fact into the rival's profile and ask again under greedy decoding. Two controls separate content from placement: a...
-
04
R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection
Pushp, Vaibhav Prajapati, Himangshu Sarma
cs.CL · cs.AI
Recent advances in paraphrase detection reveal a fundamental trade-off: large language models achieve high accuracy but require high computation, while efficient Siamese-BERT variants offer practical scalability with reduced transparency in rationale generation. We present R-DEIM Net, a 76M-parameter dual-expert architecture exploring whether moderate-scale models can achieve competitive accuracy on paraphrase detection while enabling...
-
05
Return or Revise? Learning When Revision Helps Retrieval-Augmented QA
Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup, Grant Erdmann
cs.CL · cs.IR · cs.LG
We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we grade both the returned draft and its candidate revision under the same correctness judge, which makes repair, harm, and the...
-
06
How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure
Dipankar Sarkar
cs.CL · cs.AI · cs.LG
Evaluations of LLM systems routinely average over small prompt sets and report models as a ranked table. We ask how much confidence such a table deserves, using LLM-based prompt-structure inference as the case study: eight open model variants across five families and 8B to 675B parameters, caching disabled, 293 raw intermediate representations persisted. The measured phenomenon is unstable to begin with. Identical calls do not reliably...
-
07
Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases
Tapan Parikh
cs.CL · cs.AI
Language models advise people, keep them company, and write software while they sleep. Measuring what they do is hard: behavior has to be sampled repeatedly across models, prompts and releases, most of it lives in unstructured text that has to be coded before it can be counted, and the result has to be legible and rigorous enough to meaningfully compare models and vendors. To address these constraints, we present a simple, cheap, scalable,...
-
08
Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation
Tobias Deußer, Abhishek Pillai, Aurelio F. Bariviera, Dhananjay Bhardwaj, Lorenz Sparrenberg, David Berghaus,...
cs.CL · cs.AI
Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but verifiable grounding in the authoritative text. Large language models are attractive for this task, yet the models that firms can realistically deploy on-premise are compact ones, and compact models hallucinate obligations. We study whether a carefully domain-adapted retrieval-augmented...
-
09
An Empirical Study of VLM Pipelines for Long-Document QA
Kenan E. Ak, Jay Mohta, Gwang Gook Lee, Yan Xu, Dimitrios Dimitriadis
cs.CL · cs.AI · cs.CV · cs.IR
Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model agentically or as a static pipeline. We study these choices on two long-document QA benchmarks with both frontier API and...
-
10
Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations
Yeeun Chae, Yewon Choi, Seunghyun Lee, IL Im
cs.CL · cs.AI
Large language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, evaluations should assess not only distributional fidelity within countries but also whether differences across countries are preserved. However, existing distance-based metrics such as Jensen--Shannon divergence (JSD) do not directly capture such cross-country differences. To...
-
11
Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language
Toqeer Ehsan, Miriam Butt, Sarmad Hussain, Hassan Alhuzali, Ali Al-Laith
cs.CL · cs.AI
We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing. This paper offers four major contributions: 1) the conversion of the CLE-UTB phrase structure treebank into a dependency treebank by developing language-specific head-word and phrase-to-dependency label mapping rules; 2) a novel sequence labeling scheme that transforms the...
-
12
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Pavel Tikhonov, Anton Korznikov, Matvey Mikhalchuk, Nikita Dragunov, Temurbek Rahmatullaev, Polina Druzhinina, Anton...
cs.CL · cs.AI
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition Linearity Hypothesis}. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather...
-
13
CORDIAL: Calibrating Ordinal LLM Outputs from Few Labels
Xiangwei Wang, Peng Wang, Saman Halgamuge
cs.CL · cs.LG
A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compressed or exaggerated, and biased in a consistent direction. We propose CORDIAL, which treats the model's output as a noisy reading of the true label and corrects it with a channel of five interpretable parameters. The channel is small enough for its posterior to be averaged from a handful of...
-
14
Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages
Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu, Paul Azunre, Joel Budu, Lawrence A. Adu-Gyamfi
cs.CL · cs.AI
This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR...
-
15
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
Xinyue Wang, Jiacheng Pang, Kun Zhou, Kexin Zhang, Defu Cao, Fan Feng, Faisal, Songyao Jin, Yan Liu, Biwei Huang
cs.CL · cs.AI · cs.CE
We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, continuous-signal perception and zero-shot forecasting from the other, and fuses the two in a shared representation space where both modalities are...
-
16
TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar)
Bhuvanesh Verma, Ali Abusaleh, Alexander Mehler
cs.CL · cs.LG
Arabic-language stance detection remains challenging, and previous shared-task systems have largely relied on multitask learning and ensembles. While these systems achieve state-of-the-art performance, their applicability and transferability are limited by the additional complexity introduced by multitask learning.To reduce this complexity, we introduce $\texttt{CLASP-Ar}$, which reformulates the task as cloze-style masked language modeling....
-
17
TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification
Ali Abusaleh, Bhuvanesh Verma, Alexander Mehler
cs.CL · cs.AI · cs.LG
We present TTLab's submission to the AlexandriaX-2026 Subtask~3 on Arabic MT error span detection and classification. Our system frames the task as token-level classification over surface forms, preserving character offsets to ensure exact alignment with the evaluation metric. To handle severe label imbalance, we employ a focal loss with class weighting and dialect-specific decoding thresholds. Among six Arabic pre-trained encoders, MARBERTv2...
-
18
IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
Xingyu Wu, Yuchen Yan, Zhengxi Lu, Siqi Chen, Xin ZHANG, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Jian Shao, Jun...
cs.CL · cs.AI
Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based...
-
19
agentic-ger: terminology recovery in long-form speech using global context
Yanqiao Zhu, Wupeng Wang, Zhifu Gao, Xiangang Li, Xie Chen
cs.CL · cs.AI
Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-specific terminology remains challenging. Motivated by the world knowledge and contextual capability of large language models (LLMs), we propose Agentic-GER, an LLM-based agent for terminology correction in long-form speech. The agent uses global context from the full...
-
20
Rufus-Air: An Open LLM Post-Training Recipe
Chia-Yuan Chang, Renyuan Cheng, Rui Feng, Xiaotian Han, Yuan He, Hongye Jin, Linwei Li, Shiyang Li, Fenglin Liu, Xin...
cs.CL · cs.AI · cs.LG
Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and stagewise results needed to reproduce the recipe. Stages progress from basic to advanced capabilities and from hard, verifiable...
-
21
From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring
Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan, Arash Hajikhani
cs.CL · cs.AI
Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large language models (LLMs) enable new possibilities for extracting and structuring information from long and unstructured policy documents. This paper presents an...
-
22
ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Hamdy Mubarak, George Mikros, Abul...
cs.CL · cs.AI
ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate detection in Arabic memes, while Track B addresses harmful prompt detection for Arabic LLM safety evaluation. In total, 58 teams registered, 35 participated in the final evaluation, and 27 submitted system-description papers. Participating teams explored models such as AraBERT, Jais, and Qwen3-VL....
-
23
Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams
Ali Habibullah, Yazan Alshoibi, Mohammad Alshiekh, Salman Khan, Naeemullah Khan
cs.CL · cs.AI · cs.CY
One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show its pitfalls we grade a practical Computer Vision exam ($570$ dual-graded students) under $171$ configurations spanning closed and open-weights models; the best reaches mean absolute error $1.64/35$, below the $2.61/35$ two human graders achieve against each other. The catch is the prompt: a...
-
24
Reasoning Instructions Can Break Answer Decoding in Vision--Language Models
Zeyan Li, Siyuan Qiu, Jianfeng Xu
cs.CL · cs.AI
Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits before the model generates any rationale. We call this CoT-prefix scoring. On ScienceQA, Qwen2.5-VL-7B drops from 80.76% to 45.48%, and across five option-content permutations 93.54% of CoT-prefix predictions select the first slot. Condition-matched linear probes recover 78.94% from the same hidden...
-
25
No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow
Prasann Singhal, Amanda Bertsch, Jacob Steinhardt, Sewon Min
cs.CL · cs.AI
Given a large corpus, the questions one might ask can vary -- from "When was the first human heart transplant?" to "What are all the contradictory claims in this literature?" -- but what makes some questions more challenging than others? In this work, we define a notion of Corpus Task Complexity (CTC) that characterizes tasks by how their difficulty grows with corpus size; for instance, a retrieval query only requires a single linear pass...
-
26
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Ziyang Zhang, Yubin Jing, Yuanhao Zeng, Yuyao Li, Haofan Wang, Yichen Gong
cs.CL · cs.AI · cs.LG
We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work on subliminal learning shows that information about these updates can pass through unrelated generations, but has largely focused on traits or preferences using extensive teacher outputs. We introduce Active Taskless Distillation (ATD), which achieves capability transfer...
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.