cs.CL · 2026-06-13 · No. 22
Computation and Language, 2026-06-13.
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
Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen, Avinash Atreya, Hanjie Chen, Vicente Ordonez
cs.CL · cs.AI
Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented...
-
02
Operadic consistency: a label-free signal for compositional reasoning failures in LLMs
Nathaniel Bottman, Yinhong Liu, Kyle Richardson
cs.CL · cs.LG
Detecting LLM reasoning failures at inference time without ground-truth labels has motivated a wide range of confidence baselines, including self-consistency, semantic entropy, and P(True), built on within-question sampling and self-evaluation. Operad theory, the formalism for systems built by iterated substitution, suggests a complementary diagnostic: a model's direct answer to a compositional query should agree with the answer it produces...
-
03
SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation
Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková, Viktória Ondrejová
cs.CL · cs.AI · cs.LG
We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU...
-
04
One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders
Minghao Luo, Liang Chen
cs.CL · cs.AI
Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: generative recommenders may consume polluted web content, such as fake reviews and promotional pages crafted to mislead recommendations. We ask: to what extent do search-augmented LLMs become unwitting promoters of fake products when consuming polluted retrieval results? To answer this, we introduce FORGE (Fake...
-
05
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li,...
cs.CL · cs.AI · cs.LG · cs.MM · cs.RO
Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing...
-
06
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya, Arijit Roy, Sriparna Saha
cs.CL · cs.AI
Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing...
-
07
Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations
Xinxin Li, Huiyao Chen, Meishan Zhang, Yunxin Li, Zulong Chen, Zhibo Ren, Xiaoqing Dong Baotian Hu, Min Zhang
cs.CL · cs.AI
Automatic speech recognition (ASR) correction has traditionally focused on isolated utterances or short local contexts. However, as text and speech become increasingly interleaved in long interactions, ASR correction requires conversation-level contextual evidence. Existing ASR correction methods often rely on the current hypothesis or concatenate raw dialogue history. In such contexts, sparse correction evidence can be difficult to locate...
-
08
S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
Mohammed Bouri, Mohammed Erradi, Adnane Saoud
cs.CL · cs.LG
Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor...
-
09
IVIE: A Neuro-symbolic Approach to Incremental and Validated Generation of Interactive Fiction Worlds
Micaela Vaucher, Santiago Silveira, Santiago Góngora, Luis Chiruzzo
cs.CL · cs.AI
Computational creativity in Interactive Fiction faces a fundamental tension: Large Language Models (LLM) may produce creative narratives but struggle with world coherence, while symbolic systems ensure consistency but lack creative flexibility. We present IVIE (Incremental & Validated Interactive Experiences), a neuro-symbolic approach to generating complete and playable interactive fiction worlds from scratch. Building upon PAYADOR's...
-
10
Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization
Mariia Onyshchuk, Maksym-Vasyl Tarnavskyi, Marta Sumyk
cs.CL · cs.LG
Optimal transport (OT) has been shown to detect hallucinations in neural machine translation (NMT) by measuring the geometric distance between cross-attention distributions and a reference distribution, without any supervision. We extend this analysis to all six decoder layers of the Fairseq DE-EN model ($N=3{,}414$), showing that Wass-to-Unif and Wass-to-Data are complementary detectors specialised across hallucination types, that detection...
-
11
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
Minjae Kim, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang
cs.CL · cs.AI · cs.LG
Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on...
-
12
NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning
Feng Lyu, Huiqin Yan, Sijing Duan, Hao Wu, Shuang Gu, Xue Qiao, Weixu Zhang, Haolun Wu
cs.CL · cs.AI
The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content deviates from source news, still remain a critical issue in LLM-based TLS and are not well studied in existing works. To bridge this gap, we identify two primary types of hallucinations: unfaithful content during news summarization and information omission in...
-
13
NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation
Dongwook Lee, Youngho Cho, Sangkwon Park, Heeseung Kim, Sungroh Yoon
cs.CL · cs.AI · cs.SD
Simultaneous speech-to-speech translation aims to enable near-real-time communication by minimizing latency, offering a compelling, real-time alternative to the high latency of consecutive translation. However, the excessive pursuit of low latency often results in fragmented chunk-wise speech. Consequently, listeners are subjected to an unnatural acoustic flow punctuated by frequent pauses, which could increase their cognitive load. To bridge...
-
14
G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents
Minjun Choi, Yoonjin Jang, Sangwon Youn, Youngjoong Ko
cs.CL · cs.AI
While Large Language Models (LLMs) have advanced open-domain dialogue systems, maintaining long-term consistency remains a challenge due to inherent limitations in long-context reasoning and the inefficiency of processing extensive raw text. Existing approaches typically rely on either unstructured memory storage, which is prone to information loss, or computationally expensive LLMs that incur high latency. To address these limitations, we...
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.