Dialog
-
RUMBA: Russian User Memory Benchmark
2026-07-23 15:52:31Elizaveta Shevtsova, Inna Glebkina, Mark Baushenko, Pavel Gulyaev, Alena FenogenovaAbstract
The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning. To address this, we introduce RUMBA (Russian User Memory BenchmArk) - a new benchmark for long-term conversational memory that provides a fine-grained taxonomy of memory-centric question types and a unified methodology accounting for semantic type, session scope, temporal reasoning, and the explicitness of temporal expressions. RUMBA consists of timestamped user-assistant dialogues with QA pairs requiring retrieval, combination, and reasoning across sessions. While designed for Russian, we also provide an aligned English subset under the same methodology. We evaluate contemporary memory systems and long-context models, and show how RUMBA serves as a diagnostic tool to analyze model behavior across benchmark slices and identify strengths and failure modes of different memory mechanisms.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21447
PDF
-
Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications
2026-07-23 11:09:56Gregor Endler, Sebastian Kraus, Lukas StappenAbstract
Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood. In the automotive domain, this enables intuitive and humanlike in-car dialogue experiences. However, integrating these end-to-end assistants limits architectural options for programmable domain-specific safeguards. This paper discusses two implementation approaches for S2S guardrails: transcript-based and tool-based. Through an empirical evaluation, we demonstrate that both strategies are insufficient for industrial deployment in most cases due to prohibitive latency (delaying each answer by 0 to 1.4 seconds even for computationally cheap checks) and technical impediments (like potentially non-deterministic tool call behavior). Finally, we outline open challenges for S2S guardrails in the automotive context.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21180
PDF
-
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning
2026-07-23 09:35:34Qinfeng Li, Yuntai Bao, Xinyan Yu, Hongze Chen, Wenqi Zhang, Xuhong ZhangAbstract
Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, compress, or discard as interactions accumulate. Heuristic memory methods rely on subjective, task-specific rules, which can misalign with downstream objectives and limit cross-task adaptability. RL-based methods, by contrast, learn from task feedback but mainly use outcome- or module-level rewards. These coarse signals indicate task success but cannot identify which intermediate memory contents support the final answer, creating a fine-grained credit-assignment bottleneck. However, constructing such process feedback is prohibitively difficult because intermediate memory decisions lack unique ground-truth targets, while the appropriate credit varies with the agent's uncertain reasoning trajectory and therefore cannot be specified in advance. We propose AttriMem, an attribution-guided process-feedback framework for learning memory-construction policies with RL. AttriMem augments the global outcome reward with local rewards derived from token-level contributions to the final answer. Experiments on long-horizon dialogue question answering show that AttriMem outperforms retrieval-based, heuristic, and RL-based baselines, generalizes across benchmarks and answer models, stabilizes RL optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21106
PDF
-
CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages
2026-07-23 08:02:44Muhammad Dehan Al Kautsar, Salsabila Pranida, Bilal Elbouardi, Fajri KotoAbstract
Culture is lived through conversation, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CultureTalk-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CultureTalk-ID introduces three complementary tasks, namely dialogue-based multiple-choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language.
Abstract (translated)
URL
https://arxiv.org/abs/2607.21016
PDF
-
Can Conversational AI loosen Us-Versus-Them Boundaries? The Effects of Common, Dual, and Separate Identity Framings on Pro-Immigrant Intergroup Helping
2026-07-22 17:19:31Oluwadamilola Jeboda, John F. Dovidio, Jonas R. KunstAbstract
Rising immigration has intensified intergroup tensions in many countries. Traditional bias-reduction programs remain difficult to scale and increasingly constrained by U.S. policy. This preregistered experiment tested whether conversational AI can shift how majority-group members categorize and relate to Latine immigrants. Drawing on the common ingroup identity model, a quota-representative national sample of 658 non-Latine White U.S. adults completed five rounds of dialogue with a LLM (GPT-4o). The model was instructed to frame Latine immigrants in terms of a common ingroup identity (a shared American identity), a dual identity (both Latine and American), or a separate identity (distinct cultural boundaries), or to discuss an unrelated topic in a control condition. The manipulations altered categorization: relative to control, common ingroup identity and dual identity conversations lowered separate categorization, and dual identity conversations raised dual categorization. Although direct effects on behavior and pro-diversity beliefs were nonsignificant, willingness to act was significantly higher in the conditions emphasizing a superordinate identity (common ingroup and dual identity). A path model further revealed indirect associations: both conditions reduced separate categorization, which in turn correlated with greater willingness to act. Semantic similarity analyses of the transcripts confirmed that conversations tracked their assigned narratives; participants' convergence with shared-identity language related positively, and with separate-identity language negatively, to willingness to act. These effects were largely consistent across moderators (need for closure, openness to experience, and political orientation). The findings show that brief AI conversations can loosen us-versus-them boundaries while underscoring the gap between cognitive recategorization and behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2608.19220
PDF
-
Evaluating the Effectiveness of Persona Simulation in Opinion Prediction with GPT-4.1
2026-07-22 15:00:16Sarah Y. Li, Ziyu YaoAbstract
Persona simulation involves utilizing large language models (LLMs) to anticipate human choices or interactions based on specific characteristic information. To further understand current limitations and future directions, we tested persona simulation in opinion prediction with GPT-4.1 (knowledge cutoff by June 2024). Using personas from nine U.S. states provided by Columbia University's Personas dataset, GPT-4.1 accurately predicted 2024 election outcomes in eight out of the nine states, only failing in one of the swing states. We then focused on opinions related to medicine and healthcare. With the American Trends Panel Wave 123 dataset from Pew Research Center, GPT-4.1 was able to anticipate beliefs about childhood vaccines with an accuracy of up to 0.94. Furthermore, we applied GPT-4.1 to generate conversations among personas and observed that the simulated dialogues and opinions adhered well to personas' personalities and backgrounds, albeit lacking natural human-like flow. Persona simulation proves to be a promising application of artificial intelligence as long as biases are addressed. In the near future, it will be beneficial to apply it to opinion analysis and reaction prediction in diverse fields ranging from public health to lawmaking to economics.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20589
PDF
-
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans
2026-07-22 13:53:57Wentao Jiang, Youchen Xie, Haidi Fan, Yajing Chen, Xin Wang, Ye Shi, Jingya WangAbstract
Existing co-speech gesture generation methods are predominantly studied in offline settings, where gestures are synthesized from complete speech segments. However, interactive digital humans in real-world scenarios are required to generate speech-synchronous gestures online, using only currently available response audio under strict latency constraints. As a result, prior methods are unsuitable for real-time interaction, as they either rely on future speech information or incur substantial inference delay. In this paper, we formulate online co-speech gesture generation for interactive digital humans and propose a real-time interactive framework that couples a streaming speech response module with an online gesture generation module. Specifically, the gesture generator is designed as a causal multimodal autoregressive model that predicts body motion from streaming response speech and motion history, enabling low-latency and speech-aligned gesture synthesis without access to future speech. To support this setting, we further propose an offline data synthesis pipeline tailored to virtual companion scenarios, which leverages topic- and emotion-aware subject corpora to construct diverse human-agent dialogues and then generates co-speech gestures conditioned on the agent responses. Moreover, to bridge the gap between offline data construction and online deployment, we establish a self-evolving training loop by incorporating user feedback collected during online interaction into the data generation process, enabling continual adaptation to user preferences. Extensive experiments demonstrate that our framework achieves superior better latency-quality trade-off, stronger speech-motion synchronization, and higher user preference than competitive existing baselines. Project Page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.24909
PDF
-
From Discharge Notes to Patient Understanding: Persona-Grounded, Open-Ended Simulation of LLMs as Discharge Educators
2026-07-22 13:24:24Won Seok Jang, Zonghai Yao, Hong YuAbstract
Hospital discharge education is an interactive teaching task: a clinician adapts a discharge plan to a patient's literacy, recall, and personality. Existing LLM evaluations target static or artifact-generation tasks and do not measure patient understanding under open-ended dialogue. We introduce DischargeBench, a persona-grounded simulation in which a candidate LLM educator conducts a multi-turn session with a Virtual Patient, while an Education Monitor Agent regulates patient realism without modifying the educator, protecting the evaluation signal. We curate MIMIC-IV-Ext-DischargeBench, 477 cases over 24 ICD chapters with persona axes (personality, education level, health literacy, past-medical-history recall) for stratified analysis. Each simulation is scored on four axes -- Conversation Quality, Topic Checklist, Comprehension, and Factual Consistency -- by an LLM-as-a-Judge aligned against physician annotations. Across closed- and open-source LLMs, aggregate scores conceal clinically relevant variation across ICD chapters and patient personas; difficult personas expose coverage failures, comprehension gaps, and reduced source-answer agreement. LLM evaluation for discharge education should center patient understanding, not text quality or answer accuracy alone.
Abstract (translated)
URL
https://arxiv.org/abs/2609.20827
PDF
-
TINY_SCHILLER: A Drop-In German Drama Corpus for Small Language Models
Abstract
tiny_schiller closes the small-language-model prototyping, fine-tuning, education, and research gap for German literary text, providing a single-file, drop-in counterpart to Karpathy's tiny_shakespeare. The available German literary corpora are larger and richer, but require parser engineering before a single line of training or fine-tuning code can run. tiny_schiller is a 2.07-megabyte single file of eleven public-domain Schiller dramas, sourced from DraCor's GerDraCor export (CC0) and processed by deterministic parser engineering. Character-level, GPT-2 byte-pair encoding, and cl100k_base tokenization splits, an instruction-formatted dialogue-completion split, and 89 per-character persona splits load from a single HuggingFace call. A small language model literally reaches German literary text in one line of code.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19992
PDF
-
SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data
2026-07-22 09:25:47Zenghui Zhou, Xiaoyang Li, Xiaoxuan Qiao, Zhilang Wei, Tianming LeiAbstract
Smartphone personal assistants reason over longitudinal personal data, yet evaluating them requires context-rich evaluation data whose correct answers are known, and real device traces are too privacy-sensitive to share. To address this challenge, we present SenWorld, a physically grounded, deterministic, event-sourced digital-twin simulation that generates such data with ground truth fixed by construction. In SenWorld, personas live through a full day in a world built from real map, weather, holiday, and network data; every observable signal is archived in full-system snapshots; and each evaluation case is labeled by a pointer to an existing record rather than by post-hoc annotation or a large language model (LLM) judge. We evaluate this method with 16 personas in Beijing. The generated data closely matches the held-out real-user benchmark in category distribution (Jensen--Shannon divergence (JSD) 0.070) and in the daily rhythm of communication records (JSD below 0.1), though generated records remain shorter than real ones. Without scripted interaction, personas form a fully reciprocated dialogue subgraph and differentiated behavioral repertoires. Projected into 717 evaluation cases, the generated data exposes 78 failures in a production smartphone assistant, concentrating on call and Short Message Service (SMS) records while contacts, schedules, and alarms never fail. The snapshot pointer confirms each failure as an assistant-side retrieval error, with no LLM judge involved. Overall, SenWorld offers a privacy-safe, reproducible, and distribution-checked path to evaluation data whose labels are fixed by construction.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19949
PDF
-
Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction
2026-07-22 08:10:22Min-Jae Kim, Jun-Yeong Moon, Mujeen Sung, Gyeong-Moon ParkAbstract
Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches rely solely on audio and text. This omits crucial visual cues, such as facial expressions and gestures, as well as broader conversational contexts, which are necessary for accurate prediction. In this paper, we introduce Context-Aware Multimodal Alignment for Backchannel Prediction (CAMA-BC), a novel framework that leverages visual information through Multi-Layer Multimodal Alignment (MMA). Our alignment process comprises two stages. First, Context Alignment (MMA-CA) utilizes unlabeled dialogues with videos to capture conversational contexts. Next, Backchannel Alignment (MMA-BA) fine-tunes the representations specifically for backchannel prediction. Experimental results show that CAMA-BC significantly outperforms both existing methods and simple multimodal baselines, with particular effectiveness in recognizing complex backchannels such as empathy.
Abstract (translated)
URL
https://arxiv.org/abs/2607.22729
PDF
-
Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue
2026-07-22 07:15:59Jinqiang Wang, Tao Zhu, Huansheng NingAbstract
In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate inappropriate responses. A reliable dialogue system should proactively detect user-side conflicts before generating a response and seek clarification when necessary. However, prior work has largely focused on LLM-side conflicts, leaving user-side conflicts underexplored. To fill this gap, we construct UC-Bench, a human-annotated benchmark for evaluating user-side conflict detection. Preliminary experiments show that existing LLMs struggle with this task, especially when conflicts arise from implicit incompatibilities grounded in dialogue history. To improve lightweight LLMs with limited training data, we investigate data synthesis for user-side conflict detection. Existing synthesis methods do not explicitly model the implicit incompatibilities between historical and current user utterances, making it difficult to capture the evolution of conflicts and to generate reliably labeled implicit conflict samples. We propose SynUC, a constraint-guided synthesis method that represents user-side conflicts in a constraint space and uses the SPEAKING framework to guide traceable constraint transformations. Applying SynUC to WildChat, we construct UC-Data, a user-side conflict training set containing 2,487 samples. On UC-Bench, Qwen3.5-4B trained on UC-Data outperforms larger general-purpose LLMs such as Claude Opus 4.8, as well as the same backbone trained on data synthesized by existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19155
PDF
-
MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents
2026-07-21 11:32:41Guofeng Zhang, Yizeng Quan, Huaiyi Fang, Jianwei Lv, Jinyao Liu, Xunxu Duan, Lening An, Yu Ouyang, Junfeng WangAbstract
Multi-turn medical consultation agents must decide what to ask, adapt to patient responses, and determine when the collected evidence is sufficient. However, coupled evaluation conflates the quality of the policy-elicited history with policy-specific terminal diagnosis generation: strong generation can compensate for a thin history, while weaker generation can obscure a rich one. We introduce MedDDC-Eval, a diagnosis-decoupled testbed that treats elicited history as the comparison object and holds the history-to-diagnosis mapping constant through a shared frozen reader. Across two held-out sources, a grounded interface and an auditable diagnosis-trajectory-efficiency (D/T/E) harness measure diagnostic usefulness, information acquisition, and efficiency. Directional semantic coverage followed by deterministic one-to-one assignment yields coherent precision-recall counts for open-ended items, with at most one credited match per prediction or reference. Holding histories fixed, changing only the diagnostic reader shifts diagnosis F1 by 2.2-19.0 points and reverses 18% and 36% of pairwise policy orderings on the Record and Dialogue splits. We further apply standard Group Relative Policy Optimization (GRPO) over interactive multi-turn rollouts to post-train Qwen3-32B using diagnosis-result and trajectory feedback. On the 100-case Record and 70-case Dialogue splits, the trained policy improves over its initialization by 9.7 and 4.6 total-score points; removing either primary signal lowers held-out joint performance. These results show that MedDDC-Eval supports controlled attribution, interpretable elicited-history measurement, and evaluation-guided evidence-acquisition policy development.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18999
PDF
-
Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction
2026-07-21 11:06:25ChaoJin Zhao, Xuan JiangAbstract
Textual skills provide a lightweight way to improve frozen language-model agents, but their self-evolution normally requires a stable validation signal. Such signals are natural in mathematics or code, where an answer can be checked after it changes, yet are problematic in open-ended dialogue: changing the assistant response also changes the user's next reaction, so a logged reaction cannot directly evaluate a counterfactual response. We propose future-feedback skill evolution, which first redirects self-evolution from prescribing the current answer to predicting whether the observed answer will lead to a positive or negative subsequent user signal. This prediction task is verifiable on fixed logged tuples and therefore supports validation-gated textual optimization. The evolved feedback skill captures interpretable criteria for response quality and can subsequently serve as a diagnostic and optimization target for answer skills. On a proprietary, privacy-preserving sales-assistant dataset, careful quality filtering and a balanced resolved/unresolved split yield more than 75% prediction accuracy. Beyond this result, the central contribution is a formulation that converts otherwise moving conversational feedback into a fixed offline learning target, enabling reproducible skill evolution without placing every candidate skill in live traffic. We discuss the boundary between observational verification and counterfactual validity, and position the method as an offline optimization stage rather than a replacement for final human or online evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18973
PDF
-
Entropy in Conversational AI: Structured Unpredictability as Inferrable Interiority
Abstract
Sampling can increase response diversity without producing history-dependent behavior. We formalize a different design target, structured unpredictability, as conditional dependence between an output and a persistent hidden state beyond what an observer can infer from the transcript. A selection layer updates a low-dimensional style-and-attention state from a capacity-limited stream, generates several responses with a fixed base model, and selects for novelty and state affinity. Evaluation uses scripted sequences of independent prompt turns: the base model receives the current turn and rendered state, but not the preceding dialogue; cross-turn dependence resides in the wrapper state and response selector. A synthetic implementation validates the pipeline and matches four prospectively hash-frozen divergence features at point level. In the final real-model grid (mlx-community/Qwen2.5-1.5B-Instruct-4bit; 56 sequences per arm), the mechanism increased lexical novelty over the low-variance and consistency-only controls by 0.073 and 0.023, respectively. Its stylometric-consistency contrast with novelty-matched sampling was equivalent to zero under the registered smallest-effect rule, so the joint novelty-consistency criterion failed. The original two-part accumulation criterion also failed; a revised final-grid contrast, frozen after the powered grid, found higher consistency than the memory-reset ablation (0.028, 95% CI [0.018,0.039]), but does not establish path dependence. Twin separation was not established (0.003, 95% CI [-0.011,0.019]); the mean curve's saturating curvature matched the frozen prediction, which without separation does not support path dependence. Probe-level capability equivalence held within +/-0.10 on a near-ceiling battery, while output quality was not evaluated. All outcomes are machine-scored; no claims about perceived mind or consciousness are tested.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19044
PDF
-
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
2026-07-20 12:30:17Ganesh Senrayan, Moyuru Yamada, Ishan Jindal, Kiran PurohitAbstract
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores. We propose Exploratory-Assimilating Reflection (EAR), a framework for high initial retrieval performance and sample-efficient adaptation. EAR combines two mechanisms: Exploratory Reflection, which performs iterative search to bootstrap retrieval and collect useful experiences for each query, and Assimilating Reflection, which replays these experiences from an Experience Buffer to refine a global reranker more efficiently than methods relying only on immediate rewards. Experiments show that EAR improves retrieval by up to 17.9% over the baseline retriever on two long-term dialogue benchmarks. We also show that EAR is highly sample-efficient and robust to noisy feedback.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17879
PDF
-
TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse
Abstract
Candidate-based decoding typically selects a completion for each prompt independently, but many applications require a collection of outputs that satisfies global, non-decomposable requirements. We formulate this setting as structured multi-prompt, multi-completion selection: given a candidate pool for every prompt, select one completion per prompt to optimize a collection-level objective. We instantiate the problem in character dialogue, where each character should remain consistent across situations, each line should fit its situation, and characters and situations should remain distinguishable. Our method, TalkMatrix, generates multiple candidates for every character--situation pair and jointly selects a complete matrix using four embedding-based consistency and diversity objectives. Because a weighted sum can improve some dimensions by sacrificing another, TalkMatrix maximizes the worst-performing objective through a two-level minimax formulation. We approximately optimize the resulting discrete objective with multi-start coordinate ascent, and compare it with local, partial-matrix, and generic combinatorial search baselines. We run experiments on $50$ synthetic role-playing scenarios and $25$ curated board game scenarios where multiple characters interact in predefined situations. An LLM-as-a-judge rates matrix-level selection higher than random and independent cell-level selection baselines. These results show the value of structured selection for globally controlled dialogue generation, while our empirical validation remains specific to role-playing scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19022
PDF
-
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
2026-07-20 05:18:40Jingzhe Fang, Guozhi Xu, Yunfan Cui, Xiaochen Yang, Zhangyu HuaAbstract
AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt. We present ZifaMem, a structured memory system that organizes dialogue into session summaries, episodic memories, and a consolidated user model. Against a deployment-honest comparator that supplies the full raw dialogue history, and under a fixed LLM-as-a-judge protocol with route audits, structured memory raises pooled four-backbone emotional-intelligence scores by 11.4% (95% CI 6.3% to 17.1%), and persona grounding improves on all four backbones (Claude +42% relative). Multi-turn affect context wins a +39% net preference over a single-turn snapshot (exploratory), whereas an additional emotion state machine yields no measurable gain on any of five endpoints. Under an identical preregistered protocol, three memory systems (ZifaMem, Mem0, and filtered verbatim retrieval) each improve significantly over raw-history deployment, and ZifaMem and Mem0 are statistically equivalent within +/-5 points on the preregistered primary preference endpoint. The ZifaMem SDK, CLI, and portable Agent Skills are open-sourced at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17564
PDF
-
SALT: Salience-Aware Lexical Trie for Long-Context Compression
2026-07-20 02:20:52Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury, Shangqian Gao, Weikuan YuAbstract
As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sentence by a scalar relevance score, treating the document as an unstructured pool of words and sentences. Under tight budgets, this causes theme collapse, where the dominant theme(s) of a document consumes the budget, discarding less-frequent yet task-relevant themes. Preserving thematic coverage instead requires allocating the budget across recurring themes rather than scoring sentences in isolation. To this end, we propose SALT, a model-agnostic extractive framework that organizes per-sentence keywords into a trie ordered by sentence frequency (SF), a lightweight, reusable proxy for document thematic structure. This trie-based organization smooths memory allocation and prevents dominant themes from monopolizing the budget. Multi-anchor retrieval activates trie nodes labeled by query keywords at any depth, and the trie persists across dialogue turns, supporting multi-turn use without re-encoding the document. By preserving document themes, SALT reduces the prefill computation and memory cost of long-context prompts while remaining composable with KV-cache methods that target decoding-time latency and memory.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17486
PDF
-
EII-SCL: Harnessing Emotional Inertia for Multimodal Emotion Recognition in Conversation
2026-07-19 18:09:54Zilong Huang, Kong Aik Lee, Chong-Xin Gan, Zezhong Jin, Ruichen Zuo, Man-Wai MakAbstract
Multimodal emotion recognition in conversation (MERC) achieves accurate predictions by integrating multimodal and contextual information in dialogues. While current MERC approaches focus on modeling complex contextual dependencies in conversation, they often overlook the impact of contextual emotional inertia in emotion shift, leading to sub-optimal performance. To address this issue, we propose a novel Emotional Inertia-Informed Supervised Contrastive Learning module (EII-SCL) that informs the contrastive objective by constructing inertia-affected samples within temporal windows, effectively leveraging emotional inertia as a prior while enabling seamless integration with existing MERC models without requiring additional data. Extensive experiments on IEMOCAP and MELD show that our approach consistently outperforms state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17366
PDF
