cs.CL · 2026-09-10 · No. 111
Computation and Language, 2026-09-10.
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
IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier
Blake Stenstrom, Charangan Vasantharajan, Brian Sathianathan
cs.CL · cs.AI · cs.LG
Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet all 18 audited benchmarks score advertised model identifiers. We treat this as measurement error and give a protocol that makes it reportable. It has three parts. A gold-blind capability-binding preflight verifies that a route can execute the evaluation contract before any task reaches it; a...
-
02
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
Ayan Majumdar, Shounak Paul, Pushpdeep Singh, Ines Abdelaziz, Sayeh Jarollahi, Seungeon Lee, Krishna P. Gummadi,...
cs.CL · cs.AI · cs.CY
The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate online content remains an unanswered question. In this paper, we systematically compare two competing paradigms for Vision-Language Model (VLM) guidance: an instruction-driven approach where...
-
03
RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding
Fang Li
cs.CL · cs.AI
Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the output matrix W_out in R^(d x |V|). We propose Riemannian Language Models (RiLM), which remove that layer entirely: context unfolds as a trajectory on a Riemannian manifold, and next-token probabilities arise...
-
04
The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding
Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
cs.CL · cs.LG
Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phonemes or individual words difficult. Motivated by neuroscientific evidence that high-level semantic representations are distributed across cortical regions and evolve over slower temporal scales, we hypothesize that semantic content may provide a more suitable target for non-invasive decoding...
-
05
GANDR: Claim Auditing for Verifiable Legal Answer Generation
Chen Qian, Yimeng Wang, Yu Chen, Lingfei Wu, Andreas Stathopoulos
cs.CL · cs.AI · cs.IR
In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system cites. Current grounded-generation pipelines score the answer as a whole, so a correct conclusion can rest on fabricated or loosely matched citations and still score well. Closing this gap requires both a system built for per-claim verification and an evaluation that measures it....
-
06
DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs
Bhuvan Arora, Devesh Saraogi, Sravya Varada, Dhruv Kumar
cs.CL · cs.AI
Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situations can systematically favour some cultures over others, affecting localisation, user trust, and equitable behaviour. Existing cultural benchmarks evaluate accuracy against a single "correct" answer, making it difficult to characterise an LLM's cultural preference prior when multiple culturally...
-
07
Through the Looking Glass: Directly Reading and Writing Transformers
Mark Oskin
cs.CL · cs.LG
How many of a transformer's components decide a token? Counted by the absolute value of each unit's and channel's contribution to the logit, one prediction rests on thousands to hundreds of thousands of them. But contributions are signed, and across eighteen models the mass pushing away from the predicted token is a median of seven times the mass carrying it. Divide by the net and the count is dozens: on the baseline, 53 components carry...
-
08
Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
Jing Guan, Yachao Yang, Zhaoliang Liu, Yuyao Zhang, Fanyu Meng, Junlan Feng
cs.CL · cs.AI · cs.CR · cs.LG
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation time, yet the mechanism behind its lasting protection remains unclear. Analyzing its temporal optimization dynamics, we find that the defense emerges from an early compensatory adaptation phase...
-
09
Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training
Junwon Ko, Dong-Jae Lee, Minchan Kwon, Sunghyun Baek, Junmo Kim
cs.CL · cs.AI · cs.LG
LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as successful strategy coverage: how broadly a model realizes distinct successful strategies under a fixed rollout budget. We present Direct Diversity Optimization (DDO), an offline post-training method...
-
10
MedDeID enables locally governed clinical-text de-identification from real or synthetic training data
Stig Hellemans, Tom Stroobants, Elyne Scheurwegs, Pieter Meysman, Philippe G. Jorens, Kris Laukens
cs.CL · cs.LG
Clinical notes contain personally identifiable information (PII), restricting reuse for research and medical AI, especially when data cannot leave an institution. We developed MedDeID, an on-premises framework combining in-house annotation and synthetic-note generation with model training, inference, pseudonymisation and evaluation. On an independently annotated, adjudicated 300-note Dutch hospital benchmark, a hospital-trained compact...
-
11
Improving Cross-Lingual Token Representations by Adding a Pinch of SALT
Guillem Ramírez
cs.CL · cs.AI
Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection and sequence tagging, exposing a mismatch between training and usage. We propose SALT, a lightweight post-training method that...
-
12
When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination
Karan Parekh, Sanjana Pendyala Ravinder, Sana Mhapsekar, Medina Maloku
cs.CL · cs.AI
Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poorly characterised. We construct a contaminated corpus of 150 academic papers spanning supply chain management and medical research, injecting 450 known contaminants of three types: typographical corruption, semantic reversal, and absurd out-of-context insertion. We then evaluate Google Gemini...
-
13
Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling
Tingshuo Fan, Hongtao Mu, Tianyu Zhou, Hansen Liu, Tao Ji
cs.CL · cs.AI
When training data are limited, increasing parameter count is not the only way to improve language-model performance. A small parameter set, when repeatedly applied, can also deliver comparable performance. We study Looped GPT-BERT in the BabyLM 2026 Strict-small setting, combining GPT-BERT's masked next-token and causal language-modeling objectives with depth-wise parameter sharing. We train on a preprocessed 7.48M-word English corpus and...
-
14
Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA
Yuexin Wu, Dayou Yu, Vasile Rus
cs.CL · cs.AI
Medical question-answering datasets often contain answer labels, whereas high-quality rationales remain scarce, noisy, or costly to validate. This changes the acquisition question: rather than asking which questions should be labeled, we ask which already-labeled questions should receive rationale supervision under a fixed token budget. We study an offline version of this problem in which candidate rationales are visible to the selector but...
-
15
TEFM: Token-Efficient Faithful Modeling for Structured Data
Zhichao Hou, Lingdao Sha, Xueyu Mao, Yang Liu, Peijie Qiu, Rui Song
cs.CL · cs.LG
In this paper, we solve two fundamental obstacles in applying LLMs to critical domains: token efficiency and faithfulness. To address both constraints jointly, we present TEFM (Token-Efficient Faithful Modeling), a framework designed for structured data analysis in critical domains. TEFM achieves token efficiency by compressing lengthy structured observations into compact Behavioral Code tokens, dramatically reducing token consumption with...
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.