cs.CL · 2026-06-11 · No. 20
Computation and Language, 2026-06-11.
16 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
16 entries-
01
Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
Yeongseo Jung, Jaehyeok Kim, Eunseo Jung, Jiachuan Wang, Yongqi Zhang, Ka Chun Cheung, Simon See, Lei Chen
cs.CL · cs.LG
Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revision, causing information loss and compounding errors in long dialogues. We revisit the context compression under conversational dynamics and...
-
02
System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5
Haotao Xie
cs.CL · cs.AI
Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic...
-
03
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Chirag Chawla, Pratinav Seth, Vinay Kumar Sankarapu
cs.CL · cs.AI · cs.ET · cs.LG
Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language. Existing inference-time defenses that mix logits from a safe anchor model require both models to share a vocabulary, which rules them out for the cross-family specialists where safety is most degraded. We present ALIGNBEAM, a training-free method that lifts this restriction by translating...
-
04
Measuring Semantic Progress in Multi-turn Dialogue via Information Gain
Paul He, Shiva Kasiviswanathan, Dominik Janzing
cs.CL · cs.LG
Evaluating multi-turn dialogue is challenging because quality emerges across turns rather than within individual responses. We focus on a key dimension of information-seeking dialogue: semantic progress, defined as the accumulation of new, question-relevant, and non-redundant information over the course of a conversation. We formalize semantic progress as question-conditioned uncertainty reduction and introduce an information-theoretic metric...
-
05
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Yuchen Xian, Yang He, Yunqiu Xu, Yi Yang
cs.CL · cs.AI
Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel. Existing draft-verify methods use binary decisions: accept or fully recompute. Yet we find that many rejected tokens can be verified correctly by a slim submodel derived from the full verifier via intra-model routing, instead of the full verifier. This motivates our slim-verifier...
-
06
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao, Kejian Zhu, Lingshuai Wang, Dongqi Huang, Longxiang Wang, Shengjia...
cs.CL · cs.AI
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their...
-
07
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation
Selen Erkan, Bastian Boll, Kristian Kersting, Björn Deiseroth, Letitia Parcalabescu
cs.CL · cs.AI
Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This especially penalizes base models that may know the correct answers but lack the ability -- typically introduced in post-training -- to structure them as instructed. To overcome this, we propose soft-prompt tuning, an efficient, fair, and architecture-agnostic model...
-
08
Augmenting Molecular Language Models with Local $n$-gram Memory
Xinni Zhang, Zijing Liu, He Cao, Yu Li, Irwin King
cs.CL · cs.AI
Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies. To address this without disrupting standard tokenizers, we propose MolGram, which integrates a conditional $n$-gram memory module into molecular language models. MolGram maps local string patterns...
-
09
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxi Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang,...
cs.CL · cs.AI
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement...
-
10
GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
Hengyi Feng, Zeang Sheng, Meiyi Qiang, Meiyi Qiang, Wentao Zhang
cs.CL · cs.LG
Research on Text-Attributed Graphs (TAGs) has gained significant attention recently due to its broad applications across various real-world data scenarios, such as citation networks, e-commerce platforms, social media, and web pages. Inspired by the remarkable semantic understanding ability of Large Language Models (LLMs), there have been numerous attempts to integrate LLMs into TAGs. However, existing methods still struggle to generalize...
-
11
WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning
Yizhou Chi, Eric Chamoun, Zifeng Ding, Andreas Vlachos
cs.CL · cs.AI
Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more than final-answer accuracy: a model may be correct by recalling memorized training facts, citing fabricated evidence, or producing an unsupported causal story. We present WorldReasoner, an evaluation framework for temporally valid event forecasting....
-
12
Automated Creativity Evaluation of Language Models Across Open-Ended Tasks
Min Sen Tan, Zachary Kit Chun Choy, Syed Ali Redha Alsagoff, Nadya Yuki Wangsajaya, Mohor Banerjee, Swaagat Bikash...
cs.CL · cs.AI
Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in their creative potential. Realizing this potential requires systematic and scalable methods for evaluating creativity across diverse tasks. However, most existing creativity metrics are tightly coupled to specific tasks, embedding domain assumptions into the evaluation process, and limiting...
-
13
Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wild
Sidney Tio, Arunesh Sinha, Pradeep Varakantham
cs.CL · cs.AI
Large language models are now widely used for everyday learning, but the underlying interactions are typically unstructured chats rather than following a curriculum. Unlike formal online learning systems, these interactions carry no prior record of the student, so any estimate of what the student already knows must be inferred from the dialogue itself. We show that this gap is not closed by scaling models alone. Frontier and education-tuned...
-
14
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
Youwang Deng
cs.CL · cs.AI · cs.LG
User-side memory in LLMs is typically scored as a single "personalization" capability: given a user's history, is the output more user-aware? We show this aggregate metric hides opposite-direction failures. Memory factorises into at least three orthogonal axes -- behavioral consistency (style, voice), factual presence (recall facts in history), and factual absence (abstain when a fact is absent) -- and no single substrate wins all three....
-
15
Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents
Youwang Deng
cs.CL · cs.AI
Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat honesty -- bounding what an agent may claim at termination -- as a first-class metric for unattended autonomy, distinct from capability. We present Autopilot, an execution model that makes silent fabricated success structurally impossible rather than merely rarer. Autopilot externalizes all working...
-
16
Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness
Sawyer Zhang, Alexander Wang, Sophie Lei
cs.CL · cs.AI
End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode. The...
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.