cs.CL · 2026-08-17 · No. 87
Computation and Language, 2026-08-17.
5 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
5 entries-
01
You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model
Ziyang Luo, Zhongyao Chu, Xinjie He, Youting Wang, Xukui Qin, Runxiong Wu, Yan-Syuan Chen
cs.CL · cs.LG
A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates. This paper consolidates two research lines that address these on the same residual stream: a conditional steering probe writes the stream at mid-stack layers and recovers reasoning accuracy from a frozen backbone, and a...
-
02
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
Haonan He, Haodi Lei, Yun Luo, Haoran Zhang, Shunkai Zhang, Yizhuo Li, Shengji Tang, Zhilin Wang, Runzhe Zhan, Lei...
cs.CL · cs.AI
On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability. In this work, we study this setting by transferring proof-reasoning capabilities from the...
-
03
How Much Do Legal RAG Systems Still Hallucinate?
Souvick Das, Sallam Abualhaija, Domenico Bianculli
cs.CL · cs.AI
Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious consequences. To better understand this problem, we conduct a fine-grained analysis of hallucination behavior in eight legal RAG systems across two legal corpora, the GDPR (in English) and a national civil law (in French). Using claim-level and answer-level evaluation, we report on hallucination...
-
04
ASSERT: A Measurement Pipeline for GenAI Audits
Riccardo Fogliato, Abhinav Palia, Xiawei Wang, Emily Sheng, Chad Atalla, Jean Garcia-Gathright, Nicholas Pangakis,...
cs.CL · cs.AI · cs.CY
Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy. Researchers and stakeholders use that rate to compare systems, track regressions, and gate deployment. A reported rate reflects both the system under audit and the measurement choices behind it, so a change in the rate can leave it unclear whether the system or those choices moved. We introduce ASSERT, a...
-
05
Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models
Jean de Dieu Nyandwi, Leena Mathur, Yonatan Bisk, Robert Hawkins, Graham Neubig
cs.CL · cs.AI · cs.CV · cs.LG
Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors? This distinction is important because reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness. We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present...
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.